Instructions to use ivanenclonar/non_euclidean_sae with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAELens
How to use ivanenclonar/non_euclidean_sae 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
| library_name: saelens | |
| # SAEs for use with the SAELens library | |
| This repository contains the following SAEs: | |
| - blocks.0.hook_mlp_out | |
| Load these SAEs using SAELens as below: | |
| ```python | |
| from sae_lens import SAE | |
| sae, cfg_dict, sparsity = SAE.from_pretrained("ivanenclonar/non_euclidean_sae", "<sae_id>") | |
| ``` |