Downloads · 30 days
0
gemma-2-2b-sae
seonglae/gemma-2-2b-sae
gemma-2-2b-sae is a machine learning model from seonglae. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for saelens.
This repository contains the following SAEs: - gemma-2-2bblocks.20.hookresidpre18432topk640.000349faithful-gemma2-2b1024 - gemma-2-2bblocks.20.hookresidpre18432topk640.000349fineweb1024 - gemma-2-2bblocks.20.hookresid…
Access
Public
Updated Jul 2, 2025
Repo size
1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1 GB · 100%
At a glance
- Library
- saelens
- Access
- Public
- Created
- Apr 8, 2025
- Updated
- Jul 2, 2025
- SHA
- 8226af8d
Model card
From the Hugging Face model README
SAEs for use with the SAELens library
This repository contains the following SAEs:
- gemma-2-2b_blocks.20.hook_resid_pre_18432_topk_64_0.0003_49_faithful-gemma2-2b_1024
- gemma-2-2b_blocks.20.hook_resid_pre_18432_topk_64_0.0003_49_fineweb_1024
- gemma-2-2b_blocks.20.hook_resid_pre_18432_topk_64_0.0003_49_pile-uncopyrighted_1024
- gemma-2-2b_blocks.20.hook_resid_pre_18432_topk_64_0.0003_42_pile-uncopyrighted_1024
- gemma-2-2b_blocks.20.hook_resid_pre_18432_topk_64_0.0003_42_faithful-gemma2-2b_1024
- gemma-2-2b_blocks.20.hook_resid_pre_18432_topk_64_0.0003_42_fineweb_1024
Load these SAEs using SAELens as below:
from sae_lens import SAE
sae, cfg_dict, sparsity = SAE.from_pretrained("seonglae/gemma-2-2b-sae", "<sae_id>")
Citation
@inproceedings{cho2025faithfulsae,
title={Faithful{SAE}: Towards Capturing Faithful Features with Sparse Autoencoders
without External Datasets Dependency},
author={Seonglae Cho and Harryn Oh and Donghyun Lee and Luis Eduardo Rodrigues Vieira
and Andrew Bermingham and Ziad El Sayed},
booktitle={ACL 2025 Student Research Workshop},
year={2025},
url={https://openreview.net/forum?id=tBn9ChHGG9}
}
- Library
- saelens
- Created
- Apr 8, 2025
- Updated
- Jul 2, 2025