metadata
library_name: saelens
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>")
