Downloads · 30 days
4
100% of all-time downloads
demiant/sae-gemma-2-2b-multistage-tied-20x-l1-jump-batch-co-active-ortho-l1-10
sae-gemma-2-2b-multistage-tied-20x-l1-jump-batch-co-active-ortho-l1-10 is a machine learning model from demiant. 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: - 666669056 - 166670336 - 1000001536 - 500002816 - 833335296 - 333336576
Downloads · 30 days
4
100% of all-time downloads
All-time downloads
4
Public
Repo size
2 GB
Likes
0
Public
Click a slice to open those files.
.safetensors2 GB · 100%
From the Hugging Face model README
This repository contains the following SAEs:
Load these SAEs using SAELens as below:
from sae_lens import SAE
sae, cfg_dict, sparsity = SAE.from_pretrained("demiant/sae-gemma-2-2b-multistage-tied-20x-l1-jump-batch-co-active-ortho-l1-10", "<sae_id>")