{"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/the-emergence-of-clusters-in-self-attention-1","title":"The emergence of clusters in self-attention dynamics","arxiv_id":"2305.05465","date":"2023-05-09","proceeding":"NeurIPS 2023 11","authors":["Borjan Geshkovski","Cyril Letrouit","Yury Polyanskiy","Philippe Rigollet"],"abstract":"Viewing Transformers as interacting particle systems, we describe the geometry of learned representations when the weights are not time dependent. We show that particles, representing tokens, tend to cluster toward particular limiting objects as time tends to infinity. Cluster locations are determined by the initial tokens, confirming context-awareness of representations learned by Transformers. Using techniques from dynamical systems and partial differential equations, we show that the type of limiting object that emerges depends on the spectrum of the value matrix. Additionally, in the one-dimensional case we prove that the self-attention matrix converges to a low-rank Boolean matrix. The combination of these results mathematically confirms the empirical observation made by Vaswani et al. [VSP'17] that leaders appear in a sequence of tokens when processed by Transformers.","url_abs":"https://arxiv.org/abs/2305.05465v6","url_pdf":"https://arxiv.org/pdf/2305.05465v6.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":"the-emergence-of-clusters-in-self-attention-1","repo_url":"https://github.com/borjang/2023-transformers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.05465","atlas_url":"https://app.syntology.ai/?focus=2305.05465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05465"}},"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/borjang/2023-transformers","reach":null}],"summary":{"ran_fixture":2},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"1cd80897f3b75933","entry":"calculate_distance_from_viewing_direction","repo":"borjang/2023-transformers","repo_kind":"official","path":"clustering-Tformers.py","file_url":"https://github.com/borjang/2023-transformers/blob/HEAD/clustering-Tformers.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1cd80897f3b75933"}},{"code_sha256_prefix":"a6926dc483730c8b","entry":"get_dynamics","repo":"borjang/2023-transformers","repo_kind":"official","path":"clustering-Tformers.py","file_url":"https://github.com/borjang/2023-transformers/blob/HEAD/clustering-Tformers.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a6926dc483730c8b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}