Downloads · 30 days
5
28% of all-time downloads
HuFY-dev/tanh_sae
tanh_sae is a machine learning model from HuFY-dev. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
Source code [dev branch]: https://github.com/HuFY-dev/sparseautoencoder/tree/dev
Downloads · 30 days
5
28% of all-time downloads
All-time downloads
18
Public
Parameters
227M
1.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.pt907 MB · 50%
From the Hugging Face model README
Source code [dev branch]: https://github.com/HuFY-dev/sparse_autoencoder/tree/dev
Details in this post: https://www.lesswrong.com/posts/3ZCKSArYwgg9P4hqQ/normalizing-sparse-autoencoders