{"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/outlier-dimensions-encode-task-specific","title":"Outlier Dimensions Encode Task-Specific Knowledge","arxiv_id":"2310.17715","date":"2023-10-26","proceeding":null,"authors":["William Rudman","Catherine Chen","Carsten Eickhoff"],"abstract":"Representations from large language models (LLMs) are known to be dominated by a small subset of dimensions with exceedingly high variance. Previous works have argued that although ablating these outlier dimensions in LLM representations hurts downstream performance, outlier dimensions are detrimental to the representational quality of embeddings. In this study, we investigate how fine-tuning impacts outlier dimensions and show that 1) outlier dimensions that occur in pre-training persist in fine-tuned models and 2) a single outlier dimension can complete downstream tasks with a minimal error rate. Our results suggest that outlier dimensions can encode crucial task-specific knowledge and that the value of a representation in a single outlier dimension drives downstream model decisions.","url_abs":"https://arxiv.org/abs/2310.17715v2","url_pdf":"https://arxiv.org/pdf/2310.17715v2.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":"outlier-dimensions-encode-task-specific","repo_url":"https://github.com/wrudman/outlier_dimensions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.17715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17715"}},"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":"deterministic:regex_extraction","url":"https://github.com/wrudman/outlier_dimensions","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"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":0,"samples":[{"code_sha256_prefix":"fe130fc264af990f","entry":"classification_collate_fn","repo":"wrudman/outlier_dimensions","repo_kind":"official","path":"training_utils.py","file_url":"https://github.com/wrudman/outlier_dimensions/blob/HEAD/training_utils.py","link_basis":"first_harvest_node","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":"fe130fc264af990f"}},{"code_sha256_prefix":"0998dcf462254158","entry":"collate_fn","repo":"wrudman/outlier_dimensions","repo_kind":"official","path":"analysis.py","file_url":"https://github.com/wrudman/outlier_dimensions/blob/HEAD/analysis.py","link_basis":"first_harvest_node","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":"0998dcf462254158"}},{"code_sha256_prefix":"c109fc3f8a1e51cb","entry":"flatten_list","repo":"wrudman/outlier_dimensions","repo_kind":"official","path":"analysis.py","file_url":"https://github.com/wrudman/outlier_dimensions/blob/HEAD/analysis.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c109fc3f8a1e51cb"}},{"code_sha256_prefix":"4ff638cae94d2eb4","entry":"prepare_dataloader","repo":"wrudman/outlier_dimensions","repo_kind":"official","path":"training_utils.py","file_url":"https://github.com/wrudman/outlier_dimensions/blob/HEAD/training_utils.py","link_basis":"first_harvest_node","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":"4ff638cae94d2eb4"}},{"code_sha256_prefix":"6f9960a5523b9dfb","entry":"sow_seeds","repo":"wrudman/outlier_dimensions","repo_kind":"official","path":"training_utils.py","file_url":"https://github.com/wrudman/outlier_dimensions/blob/HEAD/training_utils.py","link_basis":"first_harvest_node","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":"6f9960a5523b9dfb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}