{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:02:13Z","timestamp":1750309333506,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation of China","award":["U22B2060"],"award-info":[{"award-number":["U22B2060"]}]},{"name":"Zhujiang scholar program","award":["2021JC02X170"],"award-info":[{"award-number":["2021JC02X170"]}]},{"name":"Microsoft Research Asia Collaborative Research Grant"},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF0725100"],"award-info":[{"award-number":["2023YFF0725100"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hong Kong RGC","award":["16213620, R6020-19, AoE\/E-603\/18, T41-603\/20R, C2004-21G"],"award-info":[{"award-number":["16213620, R6020-19, AoE\/E-603\/18, T41-603\/20R, C2004-21G"]}]},{"name":"Hong Kong ITC","award":["MHX\/078\/21, PRP\/004\/22FX"],"award-info":[{"award-number":["MHX\/078\/21, PRP\/004\/22FX"]}]},{"name":"HKUST-Webank joint research lab grants"},{"name":"Guangdong Province Science and Technology Plan Project","award":["2023A0505030011"],"award-info":[{"award-number":["2023A0505030011"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671776","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"3092-3103","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Learning from Emergence: A Study on Proactively Inhibiting the Monosemantic Neurons of Artificial Neural Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6473-8221","authenticated-orcid":false,"given":"Jiachuan","family":"Wang","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7394-0082","authenticated-orcid":false,"given":"Shimin","family":"Di","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8257-5806","authenticated-orcid":false,"given":"Lei","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6693-3151","authenticated-orcid":false,"given":"Charles Wang Wai","family":"Ng","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2024. Technical report of our paper. https:\/\/github.com\/dominatorX\/MEmeLcode\/ blob\/main\/EmeL_tech_report.pdf"},{"key":"e_1_3_2_2_2_1","unstructured":"Paszke Adam Gross Sam Chintala Soumith Chanan Gregory Yang Edward DeVito Zachary Lin Zeming Desmaison Alban Antiga Luca and Lerer Adam. 2017. Automatic differentiation in PyTorch. (2017)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1907375117"},{"key":"e_1_3_2_2_4_1","volume-title":"International Conference on Machine Learning. PMLR, 2397--2430","author":"Biderman Stella","year":"2023","unstructured":"Stella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley, Kyle O'Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, et al. 2023. Pythia: A suite for analyzing large language models across training and scaling. In International Conference on Machine Learning. PMLR, 2397--2430."},{"key":"e_1_3_2_2_5_1","first-page":"e00024","article-title":"Zoom in: An introduction to circuits","volume":"5","author":"Chris Olah","year":"2020","unstructured":"Olah Chris, Cammarata Nick, Schubert Ludwig, Goh Gabriel, Petrov Michael, and Carter Shan. 2020. Zoom in: An introduction to circuits. Distill 5, 3 (2020), e00024-001.","journal-title":"Distill"},{"volume-title":"ACL (1)","author":"Dar Guy","key":"e_1_3_2_2_6_1","unstructured":"Guy Dar, Mor Geva, Ankit Gupta, and Jonathan Berant. 2023. Analyzing Transformers in Embedding Space. In ACL (1). Association for Computational Linguistics, 16124--16170."},{"volume-title":"ImageNet: A large-scale hierarchical image database","author":"Deng Jia","key":"e_1_3_2_2_7_1","unstructured":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. ImageNet: A large-scale hierarchical image database. In CVPR. IEEE Computer Society, 248--255."},{"key":"e_1_3_2_2_8_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT (1)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT (1). Association for Computational Linguistics, 4171--4186."},{"key":"e_1_3_2_2_9_1","unstructured":"Nelson Elhage Tristan Hume Catherine Olsson Neel Nanda Tom Henighan Scott Johnston Sheer El Showk Nicholas Joseph Nova DasSarma Ben Mann Danny Hernandez Amanda Askell Kamal Ndousse Andy Jones Dawn Drain Anna Chen Yuntao Bai Deep Ganguli Liane Lovitt Zac Hatfield-Dodds Jackson Kernion Tom Conerly Shauna Kravec Stanislav Fort Saurav Kadavath Josh Jacobson Eli Tran-Johnson Jared Kaplan Jack Clark Tom Brown Sam McCandlish Dario Amodei and Christopher Olah. 2022. Softmax Linear Units. Transformer Circuits Thread (2022)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"e_1_3_2_2_11_1","first-page":"e30","article-title":"Multimodal neurons in artificial neural networks","volume":"6","author":"Gabriel Goh","year":"2021","unstructured":"Goh Gabriel, Cammarata Nick, Voss Chelsea, Carter Shan, Petrov Michael, Schubert Ludwig, Radford Alec, and Olah Chris. 2021. Multimodal neurons in artificial neural networks. Distill 6, 3 (2021), e30.","journal-title":"Distill"},{"volume-title":"EMNLP (1)","author":"Geva Mor","key":"e_1_3_2_2_12_1","unstructured":"Mor Geva, Roei Schuster, Jonathan Berant, and Omer Levy. 2021. Transformer Feed-Forward Layers Are Key-Value Memories. In EMNLP (1). Association for Computational Linguistics, 5484--5495."},{"key":"e_1_3_2_2_13_1","volume-title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing. CoRR abs\/2305.01610","author":"Gurnee Wes","year":"2023","unstructured":"Wes Gurnee, Neel Nanda, Matthew Pauly, Katherine Harvey, Dmitrii Troitskii, and Dimitris Bertsimas. 2023. Finding Neurons in a Haystack: Case Studies with Sparse Probing. CoRR abs\/2305.01610 (2023)."},{"volume-title":"Neural networks: a comprehensive foundation","author":"Haykin Simon","key":"e_1_3_2_2_14_1","unstructured":"Simon Haykin. 1994. Neural networks: a comprehensive foundation. Prentice Hall PTR."},{"volume-title":"Deep Residual Learning for Image Recognition","author":"He Kaiming","key":"e_1_3_2_2_15_1","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR. IEEE Computer Society, 770--778."},{"key":"e_1_3_2_2_16_1","volume-title":"Scaling Laws for Neural Language Models. CoRR abs\/2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling Laws for Neural Language Models. CoRR abs\/2001.08361 (2020)."},{"key":"e_1_3_2_2_17_1","volume-title":"Hinton","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In NIPS. 1106--1114."},{"key":"e_1_3_2_2_18_1","volume-title":"What are artificial neural networks? Nature biotechnology 26, 2","author":"Krogh Anders","year":"2008","unstructured":"Anders Krogh. 2008. What are artificial neural networks? Nature biotechnology 26, 2 (2008), 195--197."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"e_1_3_2_2_20_1","volume-title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","author":"Liu Ze","year":"2021","unstructured":"Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. In ICCV. IEEE, 9992--10002."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"crossref","unstructured":"Wolchover Natalie. 2018. New theory cracks open the black box of deep learning. (2018).","DOI":"10.7551\/mitpress\/11909.003.0037"},{"key":"e_1_3_2_2_23_1","volume-title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks. CoRR abs\/2207.13243","author":"R\u00e4uker Tilman","year":"2022","unstructured":"Tilman R\u00e4uker, Anson Ho, Stephen Casper, and Dylan Hadfield-Menell. 2022. Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks. CoRR abs\/2207.13243 (2022)."},{"key":"e_1_3_2_2_24_1","volume-title":"A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics 5","author":"Pitts Walter McCulloch","year":"1943","unstructured":"McCulloch Warren S and Pitts Walter. 1943. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics 5 (1943), 115--133."},{"key":"e_1_3_2_2_25_1","volume-title":"Cox","author":"Saxe Andrew M.","year":"2018","unstructured":"Andrew M. Saxe, Yamini Bansal, Joel Dapello, Madhu Advani, Artemy Kolchinsky, Brendan D. Tracey, and David D. Cox. 2018. On the Information Bottleneck Theory of Deep Learning. In ICLR (Poster). OpenReview.net."},{"key":"e_1_3_2_2_26_1","volume-title":"Are Emergent Abilities of Large Language Models a Mirage? CoRR abs\/2304.15004","author":"Schaeffer Rylan","year":"2023","unstructured":"Rylan Schaeffer, Brando Miranda, and Sanmi Koyejo. 2023. Are Emergent Abilities of Large Language Models a Mirage? CoRR abs\/2304.15004 (2023)."},{"key":"e_1_3_2_2_27_1","unstructured":"Xingjian Shi Zhourong Chen Hao Wang Dit-Yan Yeung Wai-Kin Wong and Wang-chun Woo. 2015. Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. In NIPS. 802--810."},{"key":"e_1_3_2_2_28_1","unstructured":"Xingjian Shi Zhihan Gao Leonard Lausen Hao Wang Dit-Yan Yeung Wai-Kin Wong and Wang-chun Woo. 2017. Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model. In NIPS. 5617--5627."},{"key":"e_1_3_2_2_29_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In ICLR."},{"key":"e_1_3_2_2_30_1","volume-title":"Language models can explain neurons in language models. URL https:\/\/openaipublic. blob. core. windows. net\/neuron-explainer\/paper\/index. html.(Date accessed: 14.05. 2023)","author":"Steven Bills","year":"2023","unstructured":"Bills Steven, Cammarata Nick, Mossing Dan, Tillman Henk, Gao Leo, Goh Gabriel, Sutskever Ilya, Leike Jan, Wu Jeff, and Saunders William. 2023. Language models can explain neurons in language models. URL https:\/\/openaipublic. blob. core. windows. net\/neuron-explainer\/paper\/index. html.(Date accessed: 14.05. 2023) (2023)."},{"key":"e_1_3_2_2_31_1","volume-title":"Language models can explain neurons in language models. URL https:\/\/openaipublic. blob. core. windows. net\/neuron-explainer\/paper\/index. html.(Date accessed: 14.05. 2023)","author":"Steven Bills","year":"2023","unstructured":"Bills Steven, Cammarata Nick, Mossing Dan, Tillman Henk, Gao Leo, Goh Gabriel, Sutskever Ilya, Leike Jan,Wu Jeff, and Saunders William. 2023. Language models can explain neurons in language models. URL https:\/\/openaipublic. blob. core. windows. net\/neuron-explainer\/paper\/index. html.(Date accessed: 14.05. 2023) (2023)."},{"volume-title":"Going deeper with convolutions","author":"Szegedy Christian","key":"e_1_3_2_2_32_1","unstructured":"Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott E. Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2015. Going deeper with convolutions. In CVPR. IEEE Computer Society, 1--9."},{"volume-title":"Deep learning and the information bottleneck principle","author":"Tishby Naftali","key":"e_1_3_2_2_33_1","unstructured":"Naftali Tishby and Noga Zaslavsky. 2015. Deep learning and the information bottleneck principle. In ITW. IEEE, 1--5."},{"key":"e_1_3_2_2_34_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton-Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aur\u00e9lien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. CoRR abs\/2307.09288 (2023)."},{"key":"e_1_3_2_2_35_1","volume-title":"Towards Monosemanticity: Decomposing Language Models With Dictionary Learning. Transformer Circuits Thread","author":"Trenton Bricken","year":"2023","unstructured":"Bricken Trenton, Templeton Adly, Batson Joshua, Chen Brian, Jermyn Adam, Conerly Tom, Turner Nick, Anil Cem, Denison Carson, Askell Amanda, et al. 2023. Towards Monosemanticity: Decomposing Language Models With Dictionary Learning. Transformer Circuits Thread (2023)."},{"key":"e_1_3_2_2_36_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In NIPS. 5998--6008."},{"key":"e_1_3_2_2_37_1","volume-title":"Bowman","author":"Wang Alex","year":"2019","unstructured":"Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. 2019. GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding. In ICLR (Poster). OpenReview.net."},{"key":"e_1_3_2_2_38_1","volume-title":"Yu","author":"Wang Yunbo","year":"2017","unstructured":"Yunbo Wang, Mingsheng Long, Jianmin Wang, Zhifeng Gao, and Philip S. Yu. 2017. PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs. In NIPS. 879--888."},{"key":"e_1_3_2_2_39_1","volume-title":"Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. 2022. Emergent Abilities of Large Language Models. Trans. Mach. Learn. Res. 2022 (2022)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/ngeo2911"},{"key":"e_1_3_2_2_41_1","unstructured":"LeCun Yann Bengio Yoshua et al. 1995. Convolutional networks for images speech and time series. The handbook of brain theory and neural networks 3361 10 (1995) 1995."},{"key":"e_1_3_2_2_42_1","volume-title":"The Mystery and Fascination of LLMs: A Comprehensive Survey on the Interpretation and Analysis of Emergent Abilities. CoRR abs\/2311.00237","author":"Zhou Yuxiang","year":"2023","unstructured":"Yuxiang Zhou, Jiazheng Li, Yanzheng Xiang, Hanqi Yan, Lin Gui, and Yulan He. 2023. The Mystery and Fascination of LLMs: A Comprehensive Survey on the Interpretation and Analysis of Emergent Abilities. CoRR abs\/2311.00237 (2023)."}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Barcelona Spain","acronym":"KDD '24"},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671776","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671776","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:13Z","timestamp":1750291453000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671776"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":41,"alternative-id":["10.1145\/3637528.3671776","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671776","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}