This is a link post.Generated by Dalle

Background

Sparse autoencoders recover a diversity of interpretable, monosemantic features, but present an intractable problem of scale to human labelers. We investigate different techniques for generating and scoring text explanations of SAE features.

Key Findings

Open source models generate and evaluate text explanations of SAE features reasonably well, albeit somewhat worse than closed models like Claude 3.5 Sonnet.
Explanations found by LLMs are similar to explanations found by humans.
Automatically interpreting 1.5M features of GPT-2 with the current pipeline would cost $1300 in API calls to Llama 3.1 or $8500 with Claude 3.5 Sonnet. Prior methods cost ~$200k with Claude.
Code can be found at https://github.com/EleutherAI/sae-auto-interp.
We built a small dashboard to explore explanations and their scores: https://cadentj.github.io/demo/

Generating Explanations

Sparse autoencoders decompose activations into a sum of sparse feature directions. We leverage language models to generate explanations for activating text examples. Prior work [...]

The original text contained 3 images which were described by AI.

---

First published:
July 30th, 2024

Source:
https://www.lesswrong.com/posts/AhG3RJ6F5KvmKmAkd/open-source-automated-interpretability-for-sparse

---

Narrated by TYPE III AUDIO.

---

Images from the article:

“Open Source Automated Interpretability for Sparse Autoencoder Features” by kh4dien, SrGonao, jacob_drori, Nora Belrose

LessWrong (30+ Karma)