Instructions to use chanind/synthetic-model-16k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAELens
How to use chanind/synthetic-model-16k 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
Synthetic Model for SAE Training
This repository contains a SyntheticModel for use with SAELens.
Model Info
- Number of features: 16,384
- Hidden dimension: 256
- Hierarchy: Yes
- Root nodes: 32
- Total nodes: 16384
- Max depth: 3
- Feature correlation: Yes (scale 0.2)
Usage
from sae_lens.synthetic import SyntheticModel
model = SyntheticModel.from_pretrained("chanind/synthetic-model-16k")
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support