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 |
| 2026-08-14 | 1501 |
| 2026-08-18 | 1505 |
| 2026-08-19 | 1506 |
| 2026-08-21 | 1507 |
| 2026-08-22 | 1508 |
| 2026-08-23 | 1509 |
| 2026-08-24 | 1510 |
| 2026-08-25 | 1510 |
| 2026-08-26 | 1510 |
| 2026-08-28 | 1514 |
| 2026-08-29 | 1517 |
| 2026-08-30 | 1518 |
| 2026-08-31 | 1519 |
| 2026-09-01 | 1518 |
| 2026-09-03 | 1521 |
| 2026-09-04 | 1522 |
| 2026-09-05 | 1523 |
| 2026-09-07 | 1524 |
| 2026-09-08 | 1525 |
| 2026-09-09 | 1526 |
| 2026-09-11 | 1528 |
| 2026-09-12 | 1530 |
| 2026-09-14 | 1531 |
| 2026-09-15 | 1533 |
| 2026-09-16 | 1534 |
| 2026-09-17 | 1535 |
| 2026-09-18 | 1536 |
| 2026-09-19 | 1537 |
| 2026-09-20 | 1538 |
| 2026-09-22 | 1539 |
| 2026-09-23 | 1540 |
| 2026-09-24 | 1540 |
| 2026-09-25 | 1540 |
| 2026-09-26 | 1541 |
| 2026-09-28 | 1541 |
| 2026-09-29 | 1542 |
| 2026-09-30 | 1542 |
| 2026-10-01 | 1544 |
| 2026-10-02 | 1545 |
| 2026-10-03 | 1546 |
| 2026-10-05 | 1546 |
| 2026-10-06 | 1548 |
| 2026-10-07 | 1550 |
| 2026-10-08 | 1551 |
| 2026-10-09 | 1551 |
| 2026-10-10 | 1552 |
| 2026-10-11 | 1553 |
| 2026-10-12 | 1554 |
| 2026-10-13 | 1555 |
| 2026-10-14 | 1555 |
| 2026-10-15 | 1559 |
| 2026-10-16 | 1561 |
| 2026-10-17 | 1562 |
| 2026-10-18 | 1563 |
| 2026-10-19 | 1564 |
| 2026-10-20 | 1566 |
| 2026-10-21 | 1567 |
| 2026-10-22 | 1568 |
| 2026-10-23 | 1568 |
| 2026-10-24 | 1569 |
| 2026-10-25 | 1570 |
| 2026-10-26 | 1571 |
| 2026-10-27 | 1574 |
| 2026-10-29 | 1576 |
| 2026-10-30 | 1577 |
| 2026-11-01 | 1579 |
| 2026-11-02 | 1579 |
| 2026-11-04 | 1579 |
Today
— stars today
This week
+5 stars this week
This month
+33 stars this month
Momentum
40.0
growth rate 0.32%/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).