{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sparse-feature-circuits-discovering-and","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","arxiv_id":"2403.19647","date":"2024-03-28","proceeding":null,"authors":["Samuel Marks","Can Rager","Eric J. Michaud","Yonatan Belinkov","David Bau","Aaron Mueller"],"abstract":"We introduce methods for discovering and applying sparse feature circuits. These are causally implicated subnetworks of human-interpretable features for explaining language model behaviors. Circuits identified in prior work consist of polysemantic and difficult-to-interpret units like attention heads or neurons, rendering them unsuitable for many downstream applications. In contrast, sparse feature circuits enable detailed understanding of unanticipated mechanisms. Because they are based on fine-grained units, sparse feature circuits are useful for downstream tasks: We introduce SHIFT, where we improve the generalization of a classifier by ablating features that a human judges to be task-irrelevant. Finally, we demonstrate an entirely unsupervised and scalable interpretability pipeline by discovering thousands of sparse feature circuits for automatically discovered model behaviors.","url_abs":"https://arxiv.org/abs/2403.19647v3","url_pdf":"https://arxiv.org/pdf/2403.19647v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sparse-feature-circuits-discovering-and","repo_url":"https://github.com/saprmarks/feature-circuits","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sparse-feature-circuits-discovering-and","repo_url":"https://github.com/hannamw/eap-ig","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.19647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19647"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/saprmarks/feature-circuits","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hannamw/eap-ig","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"eecfb19bf7c5823f","entry":"generate_random_color","repo":"hannamw/eap-ig","repo_kind":"listed","path":"src/eap/visualization.py","file_url":"https://github.com/hannamw/eap-ig/blob/HEAD/src/eap/visualization.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eecfb19bf7c5823f"}},{"code_sha256_prefix":"994fc5fd1dd289d3","entry":"get_color","repo":"hannamw/eap-ig","repo_kind":"listed","path":"src/eap/visualization.py","file_url":"https://github.com/hannamw/eap-ig/blob/HEAD/src/eap/visualization.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"994fc5fd1dd289d3"}},{"code_sha256_prefix":"0091bc27d72797b5","entry":"cmap","repo":"hannamw/eap-ig","repo_kind":"listed","path":"src/eap/visualization.py","file_url":"https://github.com/hannamw/eap-ig/blob/HEAD/src/eap/visualization.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0091bc27d72797b5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}