---
library_name: transformers
license: mit
pipeline_tag: feature-extraction
---

# SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

This repository contains model checkpoints for Sparse Autoencoders (SAEs), as described in the paper [SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability](https://huggingface.co/papers/2503.09532).

These models can be used for feature extraction.

Project page: https://saebench.xyz.
For code, please see the [SAEBench repository](https://github.com/adamkarvonen/SAEBench).