Downloads · 30 days
0
othello_saes
adamkarvonen/othello_saes
othello_saes is a machine learning model from adamkarvonen. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repo contains several sweeps of SAEs trained on OthelloGPT, including sweeps used for the paper "Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models".
Access
Public
Updated Jan 30, 2025
Repo size
88.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.zip50.5 GB · 95%
At a glance
- Access
- Public
- Created
- May 18, 2024
- Updated
- Jan 30, 2025
- SHA
- f997cba0
Model card
From the Hugging Face model README
This repo contains several sweeps of SAEs trained on OthelloGPT, including sweeps used for the paper "Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models".
The Othello SAEs from the paper are:
othello-trained_model-layer_5-2024-05-23.zip and othello-random_model-layer_5-2024-05-23.zip
The SAEs are stored in zip files with a particular file structure. For download and usage directions, refer to https://github.com/adamkarvonen/SAE_BoardGameEval
- Created
- May 18, 2024
- Updated
- Jan 30, 2025