{"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/inferring-functionality-of-attention-heads","title":"Inferring Functionality of Attention Heads from their Parameters","arxiv_id":"2412.11965","date":"2024-12-16","proceeding":null,"authors":["Amit Elhelo","Mor Geva"],"abstract":"Attention heads are one of the building blocks of large language models (LLMs). Prior work on investigating their operation mostly focused on analyzing their behavior during inference for specific circuits or tasks. In this work, we seek a comprehensive mapping of the operations they implement in a model. We propose MAPS (Mapping Attention head ParameterS), an efficient framework that infers the functionality of attention heads from their parameters, without any model training or inference. We showcase the utility of MAPS for answering two types of questions: (a) given a predefined operation, mapping how strongly heads across the model implement it, and (b) given an attention head, inferring its salient functionality. Evaluating MAPS on 20 operations across 6 popular LLMs shows its estimations correlate with the head's outputs during inference and are causally linked to the model's predictions. Moreover, its mappings reveal attention heads of certain operations that were overlooked in previous studies, and valuable insights on function universality and architecture biases in LLMs. Next, we present an automatic pipeline and analysis that leverage MAPS to characterize the salient operations of a given head. Our pipeline produces plausible operation descriptions for most heads, as assessed by human judgment, while revealing diverse operations.","url_abs":"https://arxiv.org/abs/2412.11965v1","url_pdf":"https://arxiv.org/pdf/2412.11965v1.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":"inferring-functionality-of-attention-heads","repo_url":"https://github.com/amitelhelo/maps","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2412.11965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11965"}},"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/amitelhelo/maps","reach":{"status":"ok"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":6,"samples":[{"code_sha256_prefix":"feb7bc1c3ffe8aa9","entry":"format_output_df","repo":"amitelhelo/maps","repo_kind":"official","path":"src/paper_utils.py","file_url":"https://github.com/amitelhelo/maps/blob/HEAD/src/paper_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"feb7bc1c3ffe8aa9"}},{"code_sha256_prefix":"6e09bd61b3cbdea2","entry":"get_w_vo","repo":"amitelhelo/maps","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/amitelhelo/maps/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6e09bd61b3cbdea2"}},{"code_sha256_prefix":"a9eb8f7f16a49f10","entry":"load_dataset","repo":"amitelhelo/maps","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/amitelhelo/maps/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a9eb8f7f16a49f10"}},{"code_sha256_prefix":"1e25afc047e40d96","entry":"model_name_to_printing_name","repo":"amitelhelo/maps","repo_kind":"official","path":"src/paper_utils.py","file_url":"https://github.com/amitelhelo/maps/blob/HEAD/src/paper_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1e25afc047e40d96"}},{"code_sha256_prefix":"e5f0cb2af8697371","entry":"rearrange_heads_by_layer","repo":"amitelhelo/maps","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/amitelhelo/maps/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e5f0cb2af8697371"}},{"code_sha256_prefix":"63e58f86d4fa5333","entry":"relation_to_fixed_name","repo":"amitelhelo/maps","repo_kind":"official","path":"src/paper_utils.py","file_url":"https://github.com/amitelhelo/maps/blob/HEAD/src/paper_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"63e58f86d4fa5333"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}