{"id":20411150,"url":"https://github.com/explanare/eval-neuron-explanation","last_synced_at":"2026-06-08T10:31:23.183Z","repository":{"id":246266465,"uuid":"705417687","full_name":"explanare/eval-neuron-explanation","owner":"explanare","description":"A framework for evaluating auto-interp pipelines, i.e., natural language explanations of neurons.","archived":false,"fork":false,"pushed_at":"2024-06-26T19:15:44.000Z","size":507,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-05T03:16:18.170Z","etag":null,"topics":["causal-intervention","explanability","interpretability","neurons","probing"],"latest_commit_sha":null,"homepage":"https://aclanthology.org/2023.blackboxnlp-1.24/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/explanare.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-10-16T00:33:46.000Z","updated_at":"2024-11-21T19:38:33.000Z","dependencies_parsed_at":"2024-06-26T23:47:10.785Z","dependency_job_id":"3eb48007-0cca-4d55-b703-ec3acf1fdf8e","html_url":"https://github.com/explanare/eval-neuron-explanation","commit_stats":null,"previous_names":["explanare/eval_neuron_explanation","explanare/eval-neuron-explanation"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/explanare/eval-neuron-explanation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/explanare%2Feval-neuron-explanation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/explanare%2Feval-neuron-explanation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/explanare%2Feval-neuron-explanation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/explanare%2Feval-neuron-explanation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/explanare","download_url":"https://codeload.github.com/explanare/eval-neuron-explanation/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/explanare%2Feval-neuron-explanation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34059153,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-08T02:00:07.615Z","response_time":111,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["causal-intervention","explanability","interpretability","neurons","probing"],"created_at":"2024-11-15T05:51:27.965Z","updated_at":"2026-06-08T10:31:23.155Z","avatar_url":"https://github.com/explanare.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Rigorously Assessing Natural Language Explanations of Neurons\n\nWe develop two modes of evaluation for natural language explanations that claim individual neurons represent a concept in a text input. We apply our framework to the GPT-4-generated explanations of GPT-2 XL neurons of Bills et al. (2023) and show that even the most confident explanations have high error rates and little to no causal efficacy.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fexplanare%2Feval-neuron-explanation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fexplanare%2Feval-neuron-explanation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fexplanare%2Feval-neuron-explanation/lists"}