{"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/on-the-pitfalls-of-analyzing-individual-1","title":"On the Pitfalls of Analyzing Individual Neurons in Language Models","arxiv_id":"2110.07483","date":"2021-10-14","proceeding":"ICLR 2022 4","authors":["Omer Antverg","Yonatan Belinkov"],"abstract":"While many studies have shown that linguistic information is encoded in hidden word representations, few have studied individual neurons, to show how and in which neurons it is encoded. Among these, the common approach is to use an external probe to rank neurons according to their relevance to some linguistic attribute, and to evaluate the obtained ranking using the same probe that produced it. We show two pitfalls in this methodology: 1. It confounds distinct factors: probe quality and ranking quality. We separate them and draw conclusions on each. 2. It focuses on encoded information, rather than information that is used by the model. We show that these are not the same. We compare two recent ranking methods and a simple one we introduce, and evaluate them with regard to both of these aspects.","url_abs":"https://arxiv.org/abs/2110.07483v3","url_pdf":"https://arxiv.org/pdf/2110.07483v3.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":"on-the-pitfalls-of-analyzing-individual-1","repo_url":"https://github.com/omerant/individual-neurons","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"on-the-pitfalls-of-analyzing-individual-1","repo_url":"https://github.com/technion-cs-nlp/individual-neurons-pitfalls","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2110.07483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.07483"}},"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/technion-cs-nlp/individual-neurons-pitfalls","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/omerant/individual-neurons","reach":null}],"summary":{"ran_violates":1,"ran_honours":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"repositories":2}},"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":"3b6cdf6e6b439c53","entry":"get_diff_sum","repo":"technion-cs-nlp/individual-neurons-pitfalls","repo_kind":"official","path":"Probeless.py","file_url":"https://github.com/technion-cs-nlp/individual-neurons-pitfalls/blob/HEAD/Probeless.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3b6cdf6e6b439c53"}},{"code_sha256_prefix":"30a2855a46bb3a24","entry":"get_ranking","repo":"technion-cs-nlp/individual-neurons-pitfalls","repo_kind":"official","path":"Gaussian.py","file_url":"https://github.com/technion-cs-nlp/individual-neurons-pitfalls/blob/HEAD/Gaussian.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30a2855a46bb3a24"}},{"code_sha256_prefix":"22a5483fe0653ba5","entry":"get_ranking","repo":"omerant/individual-neurons","repo_kind":"official","path":"LinearSubset.py","file_url":"https://github.com/omerant/individual-neurons/blob/HEAD/LinearSubset.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22a5483fe0653ba5"}},{"code_sha256_prefix":"f9a3a81b6e4bc885","entry":"get_values_avg","repo":"technion-cs-nlp/individual-neurons-pitfalls","repo_kind":"official","path":"Probeless.py","file_url":"https://github.com/technion-cs-nlp/individual-neurons-pitfalls/blob/HEAD/Probeless.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9a3a81b6e4bc885"}},{"code_sha256_prefix":"bd5650b8a6ed0897","entry":"get_diff_sum","repo":"technion-cs-nlp/individual-neurons-pitfalls","repo_kind":"official","path":"Probeless.py","file_url":"https://github.com/technion-cs-nlp/individual-neurons-pitfalls/blob/HEAD/Probeless.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd5650b8a6ed0897"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}