{"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/tracrbench-generating-interpretability","title":"TracrBench: Generating Interpretability Testbeds with Large Language Models","arxiv_id":"2409.13714","date":"2024-09-07","proceeding":null,"authors":["Hannes Thurnherr","Jérémy Scheurer"],"abstract":"Achieving a mechanistic understanding of transformer-based language models is an open challenge, especially due to their large number of parameters. Moreover, the lack of ground truth mappings between model weights and their functional roles hinders the effective evaluation of interpretability methods, impeding overall progress. Tracr, a method for generating compiled transformers with inherent ground truth mappings in RASP, has been proposed to address this issue. However, manually creating a large number of models needed for verifying interpretability methods is labour-intensive and time-consuming. In this work, we present a novel approach for generating interpretability test beds using large language models (LLMs) and introduce TracrBench, a novel dataset consisting of 121 manually written and LLM-generated, human-validated RASP programs and their corresponding transformer weights. During this process, we evaluate the ability of frontier LLMs to autonomously generate RASP programs and find that this task poses significant challenges. GPT-4-turbo, with a 20-shot prompt and best-of-5 sampling, correctly implements only 57 out of 101 test programs, necessitating the manual implementation of the remaining programs. With its 121 samples, TracrBench aims to serve as a valuable testbed for evaluating and comparing interpretability methods.","url_abs":"https://arxiv.org/abs/2409.13714v1","url_pdf":"https://arxiv.org/pdf/2409.13714v1.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":"tracrbench-generating-interpretability","repo_url":"https://github.com/HannesThurnherr/TracrBench","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"tracrbench","name":"TracrBench","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.13714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13714"}},"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/HannesThurnherr/TracrBench","reach":{"status":"ok"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"a777992b2aa85e6d","entry":"load_model_from_hf","repo":"HannesThurnherr/TracrBench","repo_kind":"official","path":"transformerlens_models.py","file_url":"https://github.com/HannesThurnherr/TracrBench/blob/HEAD/transformerlens_models.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":"a777992b2aa85e6d"}},{"code_sha256_prefix":"b49e3dcbd7482d75","entry":"load_tracr_model","repo":"HannesThurnherr/TracrBench","repo_kind":"official","path":"transformerlens_models.py","file_url":"https://github.com/HannesThurnherr/TracrBench/blob/HEAD/transformerlens_models.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":"b49e3dcbd7482d75"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}