{"id":23934602,"url":"https://jbloomaus.github.io/SAELens/","last_synced_at":"2025-09-11T17:32:23.953Z","repository":{"id":209857041,"uuid":"725051425","full_name":"jbloomAus/SAELens","owner":"jbloomAus","description":"Training Sparse Autoencoders on Language Models","archived":false,"fork":false,"pushed_at":"2024-08-18T10:40:24.000Z","size":172506,"stargazers_count":313,"open_issues_count":21,"forks_count":86,"subscribers_count":8,"default_branch":"main","last_synced_at":"2024-08-18T11:13:17.049Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://jbloomaus.github.io/SAELens/","language":"HTML","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/jbloomAus.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"docs/contributing.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":"docs/roadmap.md","authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-11-29T10:37:55.000Z","updated_at":"2024-08-25T15:40:30.303Z","dependencies_parsed_at":"2024-03-25T16:17:47.227Z","dependency_job_id":"1fb34b4c-f736-4177-a2e2-da7de251160c","html_url":"https://github.com/jbloomAus/SAELens","commit_stats":null,"previous_names":["jbloomaus/mats_sae_training","jbloomaus/saelens"],"tags_count":116,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jbloomAus%2FSAELens","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jbloomAus%2FSAELens/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jbloomAus%2FSAELens/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jbloomAus%2FSAELens/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jbloomAus","download_url":"https://codeload.github.com/jbloomAus/SAELens/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":232659163,"owners_count":18557020,"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":"2025-01-06T00:35:45.987Z","updated_at":"2025-09-11T17:32:23.940Z","avatar_url":"https://github.com/jbloomAus.png","language":"HTML","funding_links":[],"categories":["Reference","Machine Learning - Interpretability"],"sub_categories":[],"readme":"\u003cimg width=\"1308\" alt=\"Screenshot 2024-03-21 at 3 08 28 pm\" src=\"https://github.com/jbloomAus/mats_sae_training/assets/69127271/209012ec-a779-4036-b4be-7b7739ea87f6\"\u003e\n\n# SAE Lens\n\n[![PyPI](https://img.shields.io/pypi/v/sae-lens?color=blue)](https://pypi.org/project/sae-lens/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![build](https://github.com/jbloomAus/SAELens/actions/workflows/build.yml/badge.svg)](https://github.com/jbloomAus/SAELens/actions/workflows/build.yml)\n[![Deploy Docs](https://github.com/jbloomAus/SAELens/actions/workflows/deploy_docs.yml/badge.svg)](https://github.com/jbloomAus/SAELens/actions/workflows/deploy_docs.yml)\n[![codecov](https://codecov.io/gh/jbloomAus/SAELens/graph/badge.svg?token=N83NGH8CGE)](https://codecov.io/gh/jbloomAus/SAELens)\n\nSAELens exists to help researchers:\n\n- Train sparse autoencoders.\n- Analyse sparse autoencoders / research mechanistic interpretability.\n- Generate insights which make it easier to create safe and aligned AI systems.\n\nPlease refer to the [documentation](https://jbloomaus.github.io/SAELens/) for information on how to:\n\n- Download and Analyse pre-trained sparse autoencoders.\n- Train your own sparse autoencoders.\n- Generate feature dashboards with the [SAE-Vis Library](https://github.com/callummcdougall/sae_vis/tree/main).\n\nSAE Lens is the result of many contributors working collectively to improve humanity's understanding of neural networks, many of whom are motivated by a desire to [safeguard humanity from risks posed by artificial intelligence](https://80000hours.org/problem-profiles/artificial-intelligence/).\n\nThis library is maintained by [Joseph Bloom](https://www.jbloomaus.com/), [Curt Tigges](https://curttigges.com/), [Anthony Duong](https://github.com/anthonyduong9) and [David Chanin](https://github.com/chanind).\n\n## Loading Pre-trained SAEs.\n\nPre-trained SAEs for various models can be imported via SAE Lens. See this [page](https://jbloomaus.github.io/SAELens/sae_table/) in the readme for a list of all SAEs.\n\n## Migrating to SAELens v6\n\nThe new v6 update is a major refactor to SAELens and changes the way training code is structured. Check out the [migration guide](https://jbloomaus.github.io/SAELens/latest/migrating/) for more details.\n\n## Tutorials\n\n- [SAE Lens + Neuronpedia](tutorials/tutorial_2_0.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://githubtocolab.com/jbloomAus/SAELens/blob/main/tutorials/tutorial_2_0.ipynb)\n- [Loading and Analysing Pre-Trained Sparse Autoencoders](tutorials/basic_loading_and_analysing.ipynb)\n  [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://githubtocolab.com/jbloomAus/SAELens/blob/main/tutorials/basic_loading_and_analysing.ipynb)\n- [Understanding SAE Features with the Logit Lens](tutorials/logits_lens_with_features.ipynb)\n  [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://githubtocolab.com/jbloomAus/SAELens/blob/main/tutorials/logits_lens_with_features.ipynb)\n- [Training a Sparse Autoencoder](tutorials/training_a_sparse_autoencoder.ipynb)\n  [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://githubtocolab.com/jbloomAus/SAELens/blob/main/tutorials/training_a_sparse_autoencoder.ipynb)\n\n## Join the Slack!\n\nFeel free to join the [Open Source Mechanistic Interpretability Slack](https://join.slack.com/t/opensourcemechanistic/shared_invite/zt-375zalm04-GFd5tdBU1yLKlu_T_JSqZQ) for support!\n\n## Citation\n\nPlease cite the package as follows:\n\n```\n@misc{bloom2024saetrainingcodebase,\n   title = {SAELens},\n   author = {Bloom, Joseph and Tigges, Curt and Duong, Anthony and Chanin, David},\n   year = {2024},\n   howpublished = {\\url{https://github.com/jbloomAus/SAELens}},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/jbloomaus.github.io%2FSAELens%2F","html_url":"https://awesome.ecosyste.ms/projects/jbloomaus.github.io%2FSAELens%2F","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/jbloomaus.github.io%2FSAELens%2F/lists"}