Instructions to use chanind/synth-sae-bench-variations with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAELens
How to use chanind/synth-sae-bench-variations 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
Commit History
-
Upload SyntheticModel misc/hierarchy-1024-8-1l-me-1.0-l0-36-4kl0-25
Verified signatureef1a360 -
Upload SyntheticModel misc/hierarchy-128-2-6l-me-1.0-l0-34-4kl0-25
Verified signature3801632
-
Upload SyntheticModel misc/hierarchy-128-128-me-1.0-l0-40-4kl0-25
Verified signatureec2c0ac -
Upload SyntheticModel misc/rand-hierarchy-16-4-32-me-0.75-l0-30-4kl0-24
Verified signatureb302de1 -
Delete misc
Verified signaturecb64700 -
Upload SyntheticModel misc/rand-hierarchy-4-64-me-1.0-l0-25-4kl0-22
Verified signature220635e -
Delete misc/rand-hierarchy-4-64-l0-142-4kl0-112
Verified signature6ddae5c -
Upload SyntheticModel misc/rand-hierarchy-4-64-me-0.5-l0-41-4kl0-37
Verified signature7bb3201 -
Upload SyntheticModel misc/rand-hierarchy-4-64-l0-142-4kl0-112
Verified signature069b236