{"id":"https://openalex.org/W4416036098","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.89","title":"A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models","display_name":"A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036098","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.89"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.89","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.89","pdf_url":"https://aclanthology.org/2025.findings-emnlp.89.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.89.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100938790","display_name":"Dong Shu","orcid":"https://orcid.org/0009-0009-9785-3934"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Shu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089884284","display_name":"Xuansheng Wu","orcid":"https://orcid.org/0000-0002-7816-7658"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuansheng Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100738980","display_name":"Haiyan Zhao","orcid":"https://orcid.org/0009-0006-5358-6895"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haiyan Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033331273","display_name":"Daking Rai","orcid":"https://orcid.org/0009-0003-3769-4974"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daking Rai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616607","display_name":"Ziyu Yao","orcid":"https://orcid.org/0009-0007-4571-3505"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyu Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007489034","display_name":"Ninghao Liu","orcid":"https://orcid.org/0000-0002-9170-2424"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ninghao Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072191151","display_name":"Mengnan Du","orcid":"https://orcid.org/0000-0002-1614-6069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengnan Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1690","last_page":"1712"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1216999962925911,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1216999962925911,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09549999982118607,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.05119999870657921,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3206999897956848},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3176000118255615},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.3091999888420105},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3046000003814697},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.2540999948978424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6126000285148621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45829999446868896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4397999942302704},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2646999955177307},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.24490000307559967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.89","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.89","pdf_url":"https://aclanthology.org/2025.findings-emnlp.89.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.89","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.89","pdf_url":"https://aclanthology.org/2025.findings-emnlp.89.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6552817191","display_name":"Collaborative Research: III: Small: Graph-Oriented Usable Interpretation","funder_award_id":"2223768","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7917778837","display_name":"Teacher-Involved Adaptive Learning with Explainable Generative AI","funder_award_id":"2507128","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G9760920","display_name":"Collaborative Research: III: Medium: Towards Effective Detection and Mitigation for Shortcut Learning: A Data Modeling Framework","funder_award_id":"2310261","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036098.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}