SAEs for use with the SAELens library

This repository contains the following SAEs:

  • layer_14/width_16k/canonical

Load these SAEs using SAELens as below:

from sae_lens import SAE

sae = SAE.from_pretrained("syzhang/gemma2-2b-it-layer-14-sae", "<sae_id>")
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support