jacobcd52 commited on
Commit
02538f4
1 Parent(s): 8a6e044

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -3
README.md CHANGED
@@ -1,11 +1,12 @@
1
  ---
2
  license: mit
3
  ---
4
- This directory contains sparse autoencoders trained on activations at various points within gpt2-small using [Neel Nanda's open source code](https://github.com/neelnanda-io/1L-Sparse-Autoencoder)
5
-
6
  Each autoencoder was trained on 1B tokens from OpenWebText.
 
 
7
 
8
- The autoencoders are named "gpt2-small_{feature_dict_size}_{point}_{layer}.pt", where:
9
  - "feature_dict_size" is the number of hidden neurons in the autoencoder
10
  - "point" is either "mlp_out" or "resid_pre"
11
  - "layer" is an integer from 0,...,11.
 
1
  ---
2
  license: mit
3
  ---
4
+ This directory contains sparse autoencoders trained on activations at various points within gpt2-small using [Neel Nanda's open source code](https://github.com/neelnanda-io/1L-Sparse-Autoencoder).
 
5
  Each autoencoder was trained on 1B tokens from OpenWebText.
6
+ A demo colab notebook is [here](https://colab.research.google.com/drive/1KeRGixXf_5GrG_7vQalG6UJQyhQd6byi?usp=sharing).
7
+
8
 
9
+ The autoencoders are named "gpt2-small_{feature_dict_size}_{point} _{layer}.pt", where:
10
  - "feature_dict_size" is the number of hidden neurons in the autoencoder
11
  - "point" is either "mlp_out" or "resid_pre"
12
  - "layer" is an integer from 0,...,11.