Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Training Sparse Autoencoders on Language Models
| Date | Stars |
|---|---|
| 2026-07-31 | 1489 |
| 2026-08-06 | 1493 |
Today
+4 stars today
This week
— stars this week
This month
— stars this month
Momentum
76.0
growth rate 0.00%/day
<img width="1308" height="532" alt="saes_pic" src="https://github.com/user-attachments/assets/2a5d752f-b261-4ee4-ad5d-ebf282321371" /> # SAE Lens [](https://pypi.org/project/sae-lens/) [](https://opensource.org/licenses/MIT) [](https://github.com/decoderesearch/SAELens/actions/workflows/build.yml) [](https://github.com/decoderesearch/SAELens/actions/workflows/deploy_docs.yml) [](https://codecov.io/gh/decoderesearch/SAELens) SAELens exists to help researchers: - Train sparse autoencoders. - Analyse sparse autoencoders / research mechanistic interpretability. - Generate insights which make it easier to create safe and aligned AI systems. SAELens inference works with any PyTorch-based model, not just TransformerLens. While we provide deep integration with TransformerLens via `HookedSAETransformer`, SAEs can be used with Hugging Face Transformers, NNsight, or any other framework by extracting activations and passing them to the SAE's `encode()` and `decode()` methods. Please refer to the [documentation](https://decoderesearch.github.io/SAELens/) for information on how to: - Download and Analyse pre-trained sparse autoencoders. - Train your own sparse autoencoders. - Generate feature dashboards with the [SAE-Vis Library](https://github.com/callummcdougall/sae_vis/tree/main). SAE 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/). This library is maintained by [Joseph Bloom](https://www.decoderesearch.com/), [Curt Tigges](https://curttigges.com/), [Anthony Duong](https://github.com/anthonyduong9) and [David Chanin](https://github.com/chanind). ## Loading Pre-trained SAEs. Pre-trained SAEs for various models can be imported via SAE Lens. See this [page](https://decoderesearch.github.io/SAELens/latest/pretrained_saes/) for a list of all SAEs. ## Migrating to SAELens v6 The new v6 update is a major refactor to SAELens and changes the way training code is structured. Check out the [migration guide](https://decoderesearch.github.io/SAELens/latest/migrating/) for more details. ## Tutorials - [SAE Lens + Neuronpedia](tutorials/tutorial_2_0.ipynb)[](https://githubtocolab.com/decoderesearch/SAELens/blob/main/tutorials/tutorial_2_0.ipynb) - [Loading and Analysing Pre-Trained Sparse Autoencoders](tutorials/basic_loading_and_analysing.ipynb) [](https://githubtocolab.com/decoderesearch/SAELens/blob/main/tutorials/basic_loading_and_analysing.ipynb) - [Understanding SAE Features with the Logit Lens](tutorials/logits_lens_with_features.ipynb) [](https://githubtocolab.com/decoderesearch/SAELens/blob/main/tutorials/logits_lens_with_features.ipynb) - [Training a Sparse Autoencoder](tutorials/training_a_sparse_autoencoder.ipynb) [](https://githubtocolab.com/decoderesearch/SAELens/blob/main/tutorials/training_a_sparse_autoencoder.ipynb) - [Training SAEs on Synthetic Data](tutorials/training_saes_on_synthetic_data.ipynb) [](https://githubtocolab.com/decoderesearch/SAELens/blob/main/tutorials/training_saes_on_synthetic_data.ipynb) - [Synt
Excerpt of 5,359 characters
Read on GitHub
209
Joseph Bloom
164
133
38
Anthony Duong
32
Dan Raviv · Sound Radix
16
14
11
11
Zhengfu He@SII · Shanghai Innovation Institute
8
7
7
5
5
4
3
3
3
3
3
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f751fc5c78830895, llm:Repository description: 'Training Sparse Autoencoders on Language Models' (Python).
matched fp:f751fc5c78830895, llm:Repository description: 'Training Sparse Autoencoders on Language Models' (Python).
matched fp:f751fc5c78830895, llm:Repository description: 'Training Sparse Autoencoders on Language Models' (Python).