{"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/disentangling-polysemantic-channels-in","title":"Disentangling Polysemantic Channels in Convolutional Neural Networks","arxiv_id":"2504.12939","date":"2025-04-17","proceeding":null,"authors":["Robin Hesse","Jonas Fischer","Simone Schaub-Meyer","Stefan Roth"],"abstract":"Mechanistic interpretability is concerned with analyzing individual components in a (convolutional) neural network (CNN) and how they form larger circuits representing decision mechanisms. These investigations are challenging since CNNs frequently learn polysemantic channels that encode distinct concepts, making them hard to interpret. To address this, we propose an algorithm to disentangle a specific kind of polysemantic channel into multiple channels, each responding to a single concept. Our approach restructures weights in a CNN, utilizing that different concepts within the same channel exhibit distinct activation patterns in the previous layer. By disentangling these polysemantic features, we enhance the interpretability of CNNs, ultimately improving explanatory techniques such as feature visualizations.","url_abs":"https://arxiv.org/abs/2504.12939v1","url_pdf":"https://arxiv.org/pdf/2504.12939v1.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":"disentangling-polysemantic-channels-in","repo_url":"https://github.com/visinf/disentangle-channels","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2504.12939","atlas_url":"https://app.syntology.ai/?focus=2504.12939","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.12939"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/visinf/disentangle-channels","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"8542e4e462554ea2","entry":"cos_similarity","repo":"visinf/disentangle-channels","repo_kind":"official","path":"get_cosine_similarities.py","file_url":"https://github.com/visinf/disentangle-channels/blob/HEAD/get_cosine_similarities.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8542e4e462554ea2"}},{"code_sha256_prefix":"315b5ee37bf1681f","entry":"get_activation","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"315b5ee37bf1681f"}},{"code_sha256_prefix":"f867b86d5acac5d6","entry":"get_gradient","repo":"visinf/disentangle-channels","repo_kind":"official","path":"get_importances_for_classes.py","file_url":"https://github.com/visinf/disentangle-channels/blob/HEAD/get_importances_for_classes.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f867b86d5acac5d6"}},{"code_sha256_prefix":"fb3704097288afa1","entry":"get_input","repo":"visinf/disentangle-channels","repo_kind":"official","path":"disentangle_channel.py","file_url":"https://github.com/visinf/disentangle-channels/blob/HEAD/disentangle_channel.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb3704097288afa1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}