Sparse Autoencoders
Collection
SAEs are tools for understanding the internal representations of neural networks. These can be loaded using https://github.com/EleutherAI/sae
•
7 items
•
Updated
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")
- Downloads last month
- 2
Model tree for EleutherAI/sae-DeepSeek-R1-Distill-Qwen-1.5B-65k
Base model
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B