File size: 655 Bytes
ca92d44 e230979 ca92d44 1eab1f3 |
1 2 3 4 5 6 7 8 9 10 |
---
license: mit
datasets:
- monology/pile-uncopyrighted
---
This contains the weights of a sparse autoencoder I trained on the residual activations of [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1). I used [The Pile (uncopyrighted)](https://huggingface.co/datasets/monology/pile-uncopyrighted) for the training data. As of right now, I have only trained a single SAE (on layer 16), though I may do more in the future.
The easiest way to use the model is with the [SAE Lens](https://github.com/jbloomAus/SAELens) library.
Here is the [training repo](https://github.com/tylercosgrove/sparse-autoencoder-mistral7b). |