{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T11:10:39Z","timestamp":1788779439484,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376633","type":"print"},{"value":"9783032376640","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-37664-0_20","type":"book-chapter","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T10:29:08Z","timestamp":1788776948000},"page":"345-361","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Concept-SAE: A Controllable and\u00a0Invertible Concept Interface for\u00a0Sparse Autoencoders"],"prefix":"10.1007","author":[{"given":"Jianrong","family":"Ding","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muxi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenchen","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,8]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Das, N., et al.: Shield: fast, practical defense and vaccination for deep learning using jpeg compression. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 196\u2013204 (2018)","DOI":"10.1145\/3219819.3219910"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"20_CR3","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"20_CR4","doi-asserted-by":"publisher","first-page":"21400","DOI":"10.52202\/068431-1555","volume":"35","author":"M Espinosa Zarlenga","year":"2022","unstructured":"Espinosa Zarlenga, M., et al.: Concept embedding models: beyond the accuracy-explainability trade-off. Adv. Neural. Inf. Process. Syst. 35, 21400\u201321413 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR5","doi-asserted-by":"publisher","first-page":"37849","DOI":"10.52202\/075280-1648","volume":"36","author":"M Espinosa Zarlenga","year":"2023","unstructured":"Espinosa Zarlenga, M., Collins, K., Dvijotham, K., Weller, A., Shams, Z., Jamnik, M.: Learning to receive help: intervention-aware concept embedding models. Adv. Neural. Inf. Process. Syst. 36, 37849\u201337875 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR6","unstructured":"Gao, L.,et al.: Scaling and evaluating sparse autoencoders. arXiv preprint arXiv:2406.04093 (2024)"},{"key":"20_CR7","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"key":"20_CR8","unstructured":"Gorton, L.: The missing curve detectors of inceptionv1: Applying sparse autoencoders to inceptionv1 early vision. arXiv preprint arXiv:2406.03662 (2024)"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"H\u00e4rle, R., et al.: Measuring and guiding monosemanticity. arXiv preprint arXiv:2506.19382 (2025)","DOI":"10.52202\/085713-5581"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"20_CR11","unstructured":"Huben, R., Cunningham, H., Smith, L.R., Ewart, A., Sharkey, L.: Sparse autoencoders find highly interpretable features in language models. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"20_CR12","unstructured":"Kantamneni, S., Engels, J., Rajamanoharan, S., Tegmark, M., Nanda, N.: Are sparse autoencoders useful? a case study in sparse probing. In: Forty-Second International Conference on Machine Learning (2025)"},{"key":"20_CR13","unstructured":"Kissane, C., Krzyzanowski, R., Bloom, J.I., Conmy, A., Nanda, N.: Interpreting attention layer outputs with sparse autoencoders. arXiv preprintarXiv:2406.17759 (2024)"},{"key":"20_CR14","unstructured":"Koh, P.W., et al.: PMLR Concept bottleneck models. In: International Conference on Machine Learning, pp. 5338\u20135348 (2020)"},{"key":"20_CR15","unstructured":"Lim, H., Choi, J., Choo, J., Schneider, S.: Sparse autoencoders reveal selective remapping of visual concepts during adaptation. arXiv preprint arXiv:2412.05276 (2024)"},{"issue":"1","key":"20_CR16","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/18.61115","volume":"37","author":"J Lin","year":"2002","unstructured":"Lin, J.: Divergence measures based on the Shannon entropy. IEEE Trans. Inf. Theory 37(1), 145\u2013151 (2002)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"20_CR18","unstructured":"Marks, L., Abdullah, A., Mendez, L., Arike, R., Torr, P., Barez, F.: Interpreting reward models in RLHF-tuned language models using sparse autoencoders (2023)"},{"key":"20_CR19","unstructured":"Marks, L., Paren, A., Krueger, D., Barez, F.: Enhancing neural network interpretability with feature-aligned sparse autoencoders. arXiv preprint arXiv:2411.01220 (2024)"},{"key":"20_CR20","unstructured":"Minegishi, G., Furuta, H., Iwasawa, Y., Matsuo, Y.: Rethinking evaluation of sparse autoencoders through the representation of polysemous words. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"20_CR21","unstructured":"Mudide, A., Engels, J., Michaud, E.J., Tegmark, M., de\u00a0Witt, C.S.: Efficient dictionary learning with switch sparse autoencoders. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Mumcu, F., Yilmaz, Y.: Multimodal attack detection for action recognition models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2967\u20132976 (2024)","DOI":"10.1109\/CVPRW63382.2024.00302"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Olah, C., Cammarata, N., Schubert, L., Goh, G., Petrov, M., Carter, S.: Zoom in: an introduction to circuits. Distill 5(3), e00024\u2013001 (2020)","DOI":"10.23915\/distill.00024.001"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Olah, C., et al.: The building blocks of interpretability. Distill 3(3), e10 (2018)","DOI":"10.23915\/distill.00010"},{"issue":"23","key":"20_CR25","doi-asserted-by":"publisher","first-page":"3311","DOI":"10.1016\/S0042-6989(97)00169-7","volume":"37","author":"BA Olshausen","year":"1997","unstructured":"Olshausen, B.A., Field, D.J.: Sparse coding with an overcomplete basis set: a strategy employed by v1? Vision. Res. 37(23), 3311\u20133325 (1997)","journal-title":"Vision. Res."},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Olson, M.L., et al.: Probing the representational power of sparse autoencoders in vision models. arXiv preprintarXiv:2508.11277 (2025)","DOI":"10.1109\/ICCVW69036.2025.00648"},{"key":"20_CR27","unstructured":"O\u2019Neill, C., Bui, T.: Sparse autoencoders enable scalable and reliable circuit identification in language models. arXiv preprint arXiv:2405.12522 (2024)"},{"key":"20_CR28","unstructured":"Paulo, G., Belrose, N.: Sparse autoencoders trained on the same data learn different features. arXiv preprint arXiv:2501.16615 (2025)"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Prakash, A., Moran, N., Garber, S., DiLillo, A., Storer, J.: Deflecting adversarial attacks with pixel deflection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8571\u20138580 (2018)","DOI":"10.1109\/CVPR.2018.00894"},{"key":"20_CR30","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"20_CR31","unstructured":"Rajamanoharan, S., et al.: Improving dictionary learning with gated sparse autoencoders. arXiv preprint arXiv:2404.16014 (2024)"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Ramaswamy, V.V., Kim, S.S., Fong, R., Russakovsky, O.: Overlooked factors in concept-based explanations: dataset choice, concept learnability, and human capability. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10932\u201310941 (2023)","DOI":"10.1109\/CVPR52729.2023.01052"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Rao, S., Mahajan, S., B\u00f6hle, M., Schiele, B.: Discover-then-name: task-agnostic concept bottlenecks via automated concept discovery. In: European Conference on Computer Vision, pp. 444\u2013461. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-72980-5_26"},{"key":"20_CR34","first-page":"21945","volume":"33","author":"H Salman","year":"2020","unstructured":"Salman, H., Sun, M., Yang, G., Kapoor, A., Kolter, J.Z.: Denoised smoothing: a provable defense for pretrained classifiers. Adv. Neural. Inf. Process. Syst. 33, 21945\u201321957 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR35","unstructured":"Sharkey, L., Braun, D., Millidge, B.: Taking features out of superposition with sparse autoencoders. AI Alignment Forum 6, 12\u201313 (2022)"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Shu, D., et al.: A survey on sparse autoencoders: Interpreting the internal mechanisms of large language models. arXiv preprint arXiv:2503.05613 (2025)","DOI":"10.18653\/v1\/2025.findings-emnlp.89"},{"key":"20_CR37","unstructured":"Stevens, S., Chao, W.L., Berger-Wolf, T., Su, Y.: Sparse autoencoders for scientifically rigorous interpretation of vision models. arXiv preprint arXiv:2502.06755 (2025)"},{"key":"20_CR38","unstructured":"Xie, C., Wang, J., Zhang, Z., Ren, Z., Yuille, A.: Mitigating adversarial effects through randomization. arXiv preprint arXiv:1711.01991 (2017)"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Xu, W., Evans, D., Qi, Y.: Feature squeezing: Detecting adversarial examples in deep neural networks. arXiv preprint arXiv:1704.01155 (2017)","DOI":"10.14722\/ndss.2018.23198"},{"key":"20_CR40","first-page":"20554","volume":"33","author":"CK Yeh","year":"2020","unstructured":"Yeh, C.K., Kim, B., Arik, S., Li, C.L., Pfister, T., Ravikumar, P.: On completeness-aware concept-based explanations in deep neural networks. Adv. Neural. Inf. Process. Syst. 33, 20554\u201320565 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"20_CR41","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1631\/FITEE.1700808","volume":"19","author":"QS Zhang","year":"2018","unstructured":"Zhang, Q.S., Zhu, S.C.: Visual interpretability for deep learning: a survey. Front. Inf. Technol. Electron. Eng. 19(1), 27\u201339 (2018)","journal-title":"Front. Inf. Technol. Electron. Eng."}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37664-0_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T10:29:26Z","timestamp":1788776966000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37664-0_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,8]]},"ISBN":["9783032376633","9783032376640"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37664-0_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,8]]},"assertion":[{"value":"8 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Naples","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}