Instructions to use jbloom/GPT2-Small-SAEs-Reformatted with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAELens
How to use jbloom/GPT2-Small-SAEs-Reformatted with SAELens:
# 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 ) - Notebooks
- Google Colab
- Kaggle
Download blocks.0.hook_resid_pre/sparsity.safetensors from jbloom/GPT2-Small-SAEs-Reformatted: direct link, hf CLI and curl.
- Browser
- Download file 98.4 kB
-
https://huggingface.co/jbloom/GPT2-Small-SAEs-Reformatted/resolve/main/blocks.0.hook_resid_pre/sparsity.safetensors
- Command line
-
hf download hf://jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre/sparsity.safetensors
-
curl -L -o sparsity.safetensors https://huggingface.co/jbloom/GPT2-Small-SAEs-Reformatted/resolve/main/blocks.0.hook_resid_pre/sparsity.safetensors
98.4 kB
- Xet hash:
- 36ddba43f662538d9dd55bd69269f35df65c612ab5ca3d069215b39d97ce65c6
- Size of remote file:
- 98.4 kB
- SHA256:
- 34e4ea473e3ff542132815cf326ce284c6ae2a3304eaf692f2226c3414d9dda8
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.