Instructions to use HuFY-dev/tanh_sae with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HuFY-dev/tanh_sae with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("HuFY-dev/tanh_sae", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Sparse Autoencoder with Tanh Activation
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
- Downloads last month
- 5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support