tim-lawson
/

mlsae-pythia-410m-deduped-x64-k32

model_hub_mixin

pytorch_model_hub_mixin

Model card Files Files and versions Community

Edit model card

This model has been pushed to the Hub using the PytorchModelHubMixin integration:

Library: [More Information Needed]
Docs: [More Information Needed]

Downloads last month: 14

Safetensors

Model size

134M params

Tensor type

F32

·

Inference API

Unable to determine this model's library. Check the docs .

Collection including tim-lawson/mlsae-pythia-410m-deduped-x64-k32

Multi-Layer Sparse Autoencoders

Single SAEs trained on the residual stream activation vectors from every transformer layer simultaneously: https://arxiv.org/abs/2409.04185 • 30 items • Updated Oct 7