{"id":19428902,"url":"https://github.com/eleutherai/features-across-time","last_synced_at":"2025-04-24T18:31:36.426Z","repository":{"id":213427343,"uuid":"734096229","full_name":"EleutherAI/features-across-time","owner":"EleutherAI","description":"Understanding how features learned by neural networks evolve throughout training","archived":false,"fork":false,"pushed_at":"2024-04-12T05:25:36.000Z","size":8312,"stargazers_count":24,"open_issues_count":1,"forks_count":1,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-04-12T13:18:58.632Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/EleutherAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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}},"created_at":"2023-12-20T21:26:04.000Z","updated_at":"2024-04-14T22:41:51.662Z","dependencies_parsed_at":"2023-12-21T00:47:51.403Z","dependency_job_id":"2c26b948-bb6a-4b69-8c5f-2abd9156fb7d","html_url":"https://github.com/EleutherAI/features-across-time","commit_stats":null,"previous_names":["eleutherai/features-across-time"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Ffeatures-across-time","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Ffeatures-across-time/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Ffeatures-across-time/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Ffeatures-across-time/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EleutherAI","download_url":"https://codeload.github.com/EleutherAI/features-across-time/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223961111,"owners_count":17232251,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":[],"created_at":"2024-11-10T14:17:06.870Z","updated_at":"2024-11-10T14:17:07.348Z","avatar_url":"https://github.com/EleutherAI.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# features-across-time\nUnderstanding how features learned by neural networks evolve throughout training\n\nNOTE: Apologies for the sloppy code in many places. We plan to clean it up in the next few weeks.\n\n### Reproduce Pythia Suite Experiments\n\nRun the following Python scripts from the command line to collect and plot data over training steps:\n\n```\npython -m scripts.preprocess.build_ngram_data --n \u003cn1\u003e \u003cn2\u003e\npython -m scripts.inference.ngrams --n \u003cn1\u003e \u003cn2\u003e\n```\n\nTo plot existing data, use:\n\n```\npython -m scripts.plot.plot_single_rows\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feleutherai%2Ffeatures-across-time","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feleutherai%2Ffeatures-across-time","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feleutherai%2Ffeatures-across-time/lists"}