Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.

This is a post to officially announce the sae-vis library, which was designed to create feature dashboards like those from Anthropic's research.

Summary

There are 2 types of visualisations supported by this library: feature-centric and prompt-centric.

The feature-centric vis is the standard from Anthropic’s post, it looks like the image below. There’s an option to navigate through different features via a dropdown in the top left.

You can see the interactive version at the GitHub repo, at _feature_vis_demo.html.

The prompt-centric vis is centred on a single user-supplied prompt, rather than a single feature. It will show you the list of features which score highest on that prompt, according to a variety of different metrics. It looks like the image below. There’s an option to navigate through different possible metrics and choices of token in your prompt via a dropdown in the top left.

You can see the interactive version at the GitHub repo, at _prompt_vis_demo.html.

 

Other links

Here are some more useful links:

  • GitHub repo
  • User Guide - Google Doc explaining how to use the library
  • Dev Guide - Google Doc explaining more about how the library was built, for if you'd like to try and extend it / build off it
  • Demo Colab - includes examples, with code explained

You might also be interested in reading about Neuronpedia, who make use of this library in their visualizations.

If you're interested in getting involved, please reach out to me or Joseph Bloom! We will also be publishing a post tomorrow, discussing some of the features we've discovered during our research.

New to LessWrong?

New Comment
8 comments, sorted by Click to highlight new comments since: Today at 5:40 AM

Thanks for open sourcing this! We've already been finding it really useful on the DeepMind mech interp team, and saved us the effort of writing our own :)

Thanks so much, really glad to hear it's been helpful!

Amazing! We found your original library super useful for our Attention SAEs research, so thanks for making this!

Thanks so much! (-:

Thanks Callum and yep we've been extensively using SAE-Vis at Neuronpedia - it's been extremely helpful for generating dashboards and it's very well maintained. We'll have a method of directly importing to Neuronpedia using the exports from SAE-Vis coming out soon.

Thanks!! Really appreciate it

is this something that can work for a hosted web version (npm i or api) 

I'm a little confused by this question. What are you proposing?