How to use from the
Use from the
SAELens library
# pip install sae-lens
from sae_lens import SAE

sae, cfg_dict, sparsity = SAE.from_pretrained(
    release = "RELEASE_ID", # e.g., "gpt2-small-res-jb". See other options in https://github.com/jbloomAus/SAELens/blob/main/sae_lens/pretrained_saes.yaml
    sae_id = "SAE_ID", # e.g., "blocks.8.hook_resid_pre". Won't always be a hook point
)

SAEs for use with the SAELens library

This repository contains the following SAEs:

  • 5926912
  • 500002816
  • 250003456
  • 750002176

Load these SAEs using SAELens as below:

from sae_lens import SAE

sae, cfg_dict, sparsity = SAE.from_pretrained("chanind/jumprelu-test", "<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. 🙋 Ask for provider support