SAEs and transcoders can be loaded using https://github.com/EleutherAI/sae:

from sae import Sae

sae = Sae.load_from_hub("EleutherAI/sae-DeepSeek-R1-Distill-Qwen-1.5B-65k", hookpoint="layers.10.mlp")

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for EleutherAI/sae-DeepSeek-R1-Distill-Qwen-1.5B-65k

Base model

Finetuned

(289)

this model

Dataset used to train EleutherAI/sae-DeepSeek-R1-Distill-Qwen-1.5B-65k