davidquarel
/

jsae.shk_64x4-sparse-8.0e-04_3.0e-03_3.0e-03_6.0e-02

Model card Files Files and versions

No model card

Downloads last month: -; Downloads are not tracked for this model. How to track

Safetensors

Model size

216k params

Tensor type

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including davidquarel/jsae.shk_64x4-sparse-8.0e-04_3.0e-03_3.0e-03_6.0e-02

jsae_xavier (mlpin -> mlpout)

Jacobian SAEs with all combo of jacobian_coeff - Layer0 in (2e-4, 4e-4, 6e-4, 8e-4) Layer1 = 3e-3 Layer2 = 3e-3 Layer3 in (2e-2, 4e-2, 6e-2, 8e-2) • 16 items • Updated Mar 2