Multi-Layer SAEs with Tuned Lens
Collection
Single SAEs trained on the residual stream activation vectors from every transformer layer simultaneously using tuned lenses.
•
16 items
•
Updated
This model has been pushed to the Hub using the PytorchModelHubMixin integration:
- Library: https://github.com/tim-lawson/mlsae
- Docs: [More Information Needed]
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.