{"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/backward-lens-projecting-language-model","title":"Backward Lens: Projecting Language Model Gradients into the Vocabulary Space","arxiv_id":"2402.12865","date":"2024-02-20","proceeding":null,"authors":["Shahar Katz","Yonatan Belinkov","Mor Geva","Lior Wolf"],"abstract":"Understanding how Transformer-based Language Models (LMs) learn and recall information is a key goal of the deep learning community. Recent interpretability methods project weights and hidden states obtained from the forward pass to the models' vocabularies, helping to uncover how information flows within LMs. In this work, we extend this methodology to LMs' backward pass and gradients. We first prove that a gradient matrix can be cast as a low-rank linear combination of its forward and backward passes' inputs. We then develop methods to project these gradients into vocabulary items and explore the mechanics of how new information is stored in the LMs' neurons.","url_abs":"https://arxiv.org/abs/2402.12865v1","url_pdf":"https://arxiv.org/pdf/2402.12865v1.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":[],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.12865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12865"}},"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/shacharKZ/BackwardLens","reach":null}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":3},"by_repo_kind":{"found_in_text":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"9db9df78c98eebe2","entry":"auto_model_to_path_config","repo":"shacharKZ/BackwardLens","repo_kind":"found_in_text","path":"llm_utils.py","file_url":"https://github.com/shacharKZ/BackwardLens/blob/HEAD/llm_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9db9df78c98eebe2"}},{"code_sha256_prefix":"ea5da01bc0fb6cd3","entry":"extract_hs_include_prefix","repo":"shacharKZ/BackwardLens","repo_kind":"found_in_text","path":"llm_utils.py","file_url":"https://github.com/shacharKZ/BackwardLens/blob/HEAD/llm_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea5da01bc0fb6cd3"}},{"code_sha256_prefix":"fb367523f3897fe7","entry":"GraphConfigs","repo":"shacharKZ/BackwardLens","repo_kind":"found_in_text","path":"llm_utils.py","file_url":"https://github.com/shacharKZ/BackwardLens/blob/HEAD/llm_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":"fb367523f3897fe7"}},{"code_sha256_prefix":"b800598af3ba2e0c","entry":"auto_model_to_config","repo":"shacharKZ/BackwardLens","repo_kind":"found_in_text","path":"llm_utils.py","file_url":"https://github.com/shacharKZ/BackwardLens/blob/HEAD/llm_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":"b800598af3ba2e0c"}},{"code_sha256_prefix":"94c41d6c78d2a364","entry":"wrap_model","repo":"shacharKZ/BackwardLens","repo_kind":"found_in_text","path":"llm_utils.py","file_url":"https://github.com/shacharKZ/BackwardLens/blob/HEAD/llm_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":"94c41d6c78d2a364"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}