Hugging Face's logo

biohub
/
ESMC-6B-sae-layer60-k128-codebook32768

Feature Extraction
Transformers
English
esmc_sae
biology
esm
protein
sparse-autoencoder
interpretability
protein-embeddings
protein-language-model
unsupervised-learning
Model card Files
xet
 Community
fmilletari-czi commited on
Commit
b19dfb5
·
verified ·
1 Parent(s): 3ae0a1f

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -30,7 +30,7 @@ The ESMC sparse autoencoders (SAEs) are unsupervised neural networks trained to
30
 
31
  Building on top of the ESMC 6B SAEs, the ESM Atlas is a map of 6.8 billion proteins covering the full breadth of life's biodiversity and more than one billion predicted structures. The SAEs enable translation of the model's internal representations into ~16,000 interpretable biological features. Learn more about how to use the ESM Atlas on the Biohub Platform.
32
 
33
- Read more about ESMC and SAEs in our [paper](https://biohub.ai/papers/esm_protein.pdf).
34
 
35
  ## Intended Use
36
 
@@ -49,10 +49,10 @@ While all SAE models can be accessed through Hugging Face, only the following fi
49
  - `ESMC-600M-sae-layer27-k64-codebook65536`
50
  - `ESMC-300M-sae-layer23-k64-codebook65536`
51
 
52
- Install `esm` from GitHub (a PyPI release is coming soon):
53
 
54
  ```
55
- pip install esm@git+https://github.com/Biohub/esm.git@main
56
  ```
57
 
58
  You can access an SAE model through Hugging Face using the code below:
 
30
 
31
  Building on top of the ESMC 6B SAEs, the ESM Atlas is a map of 6.8 billion proteins covering the full breadth of life's biodiversity and more than one billion predicted structures. The SAEs enable translation of the model's internal representations into ~16,000 interpretable biological features. Learn more about how to use the ESM Atlas on the Biohub Platform.
32
 
33
+ Read more about ESMC and SAEs in our [paper](https://www.biorxiv.org/content/10.64898/2026.06.03.729735).
34
 
35
  ## Intended Use
36
 
 
49
  - `ESMC-600M-sae-layer27-k64-codebook65536`
50
  - `ESMC-300M-sae-layer23-k64-codebook65536`
51
 
52
+ Install `esm` from PyPI:
53
 
54
  ```
55
+ pip install esm
56
  ```
57
 
58
  You can access an SAE model through Hugging Face using the code below: