Downloads · 30 days
0
jacobcd52/gpt2-small-sparse-autoencoders
gpt2-small-sparse-autoencoders is a machine learning model from jacobcd52. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This directory contains sparse autoencoders trained on activations at various points within gpt2-small using Neel Nanda's open source code. Each autoencoder was trained on 1B tokens from OpenWebText. A demo colab note…
Downloads · 30 days
0
Access
Public
Updated Nov 27, 2023
Repo size
831 MB
Likes
4
Public
Click a slice to open those files.
.pt756 MB · 100%
From the Hugging Face model README
This directory contains sparse autoencoders trained on activations at various points within gpt2-small using Neel Nanda's open source code. Each autoencoder was trained on 1B tokens from OpenWebText. A demo colab notebook is here.
The autoencoders are named "gpt2-small_{feature_dict_size}_{point} _{layer}.pt", where: