We trained a SAE to find sparse features in image embeddings. We found many meaningful, interpretable, and steerable features. We find that steering image diffusion works surprisingly well and yields predictable and high-quality generations.

You can see the feature library here. We also have an intervention playground you can try.

Key Results

We can extract interpretable features from CLIP image embeddings.
We observe a diverse set of features, e.g. golden retrievers, there being two of something, image borders, nudity, and stylistic effects.
Editing features allows for conceptual and semantic changes while maintaining generation quality and coherency.
We devise a way to preview the causal impact of a feature, and show that many features have an explanation that is consistent with what they activate for and what they cause.
Many feature edits can be stacked to perform task-relevant operations, like transferring a subject, mixing in a specific property of [...]

---

Outline:

(00:30) Key Results

(01:20) Interactive demo

(01:33) Introduction

(02:22) Steering Features

(04:22) Discovering and Interpreting Features

(06:22) Autointerpretation Labels

(07:13) Training Details

(08:34) Future Work

---

First published:
June 20th, 2024

Source:
https://www.lesswrong.com/posts/Quqekpvx8BGMMcaem/interpreting-and-steering-features-in-images

---

Narrated by TYPE III AUDIO.

“Interpreting and Steering Features in Images” by Gytis Daujotas

LessWrong (30+ Karma)

“Interpreting and Steering Features in Images” by Gytis Daujotas