{"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":"/code/chunk-and-tokenize","entry":"chunk_and_tokenize","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":5,"n_papers_ran":0,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":2,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":2},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2512.08892","paper":"/paper/arxiv-2512-08892","title":"Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"Teddy-XiongGZ/RAGLens","path":"src/sparsify/data.py","file_url":"https://github.com/Teddy-XiongGZ/RAGLens/blob/HEAD/src/sparsify/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3fafa18bde72510f","mcp_get_code":{"code_sha256":"3fafa18bde72510f"}},{"arxiv_id":"2501.18823","paper":"/paper/transcoders-beat-sparse-autoencoders-for","title":"Transcoders Beat Sparse Autoencoders for Interpretability","date":"2025-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eleutherai/sae","path":"sparsify/data.py","file_url":"https://github.com/eleutherai/sae/blob/HEAD/sparsify/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3fafa18bde72510f","mcp_get_code":{"code_sha256":"3fafa18bde72510f"}},{"arxiv_id":"2410.16090","paper":"/paper/analysing-the-residual-stream-of-language","title":"Analysing the Residual Stream of Language Models Under Knowledge Conflicts","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuzhaouoe/sae-based-representation-engineering","path":"spare/sae/data.py","file_url":"https://github.com/yuzhaouoe/sae-based-representation-engineering/blob/HEAD/spare/sae/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3fafa18bde72510f","mcp_get_code":{"code_sha256":"3fafa18bde72510f"}},{"arxiv_id":"2406.04093","paper":"/paper/scaling-and-evaluating-sparse-autoencoders","title":"Scaling and evaluating sparse autoencoders","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eleutherai/sparsify","path":"sparsify/data.py","file_url":"https://github.com/eleutherai/sparsify/blob/HEAD/sparsify/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3fafa18bde72510f","mcp_get_code":{"code_sha256":"3fafa18bde72510f"}},{"arxiv_id":"2303.08112","paper":"/paper/eliciting-latent-predictions-from","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","date":"2023-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alignmentresearch/tuned-lens","path":"tuned_lens/data.py","file_url":"https://github.com/alignmentresearch/tuned-lens/blob/HEAD/tuned_lens/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7da4d3f0adefb46","mcp_get_code":{"code_sha256":"a7da4d3f0adefb46"}}]}