Scaling laws for dictionary learning! transformer-circuits.pub/2024/april-upd…

Some small updates from the Anthropic Interpretability team:

transformer-circuits.pub/2024/april-upd…

New Anthropic research: we find that probing, a simple interpretability technique, can detect when backdoored 'sleeper agent' models are about to behave dangerously, after they pretend to be safe in training.

Check out our first alignment blog post here: anthropic.com/research/probe…

Announcing a progress update from the Google DeepMind mech interp team! Inspired by Anthropic's excellent monthly updates, we share a range of updates on our work on Sparse Autoencoders, from signs of life on interpreting steering vectors with SAEs to improving ghost grads.

Great visualisation library for Sparse Autoencoder features from Callum McDougall! My team has already been finding it super useful, go check it out:
lesswrong.com/posts/nAhy6Zqu…

I'm incredibly excited to have Craig joining us on the Anthropic Interpretability team!

I've been a huge fan of Colaboratory for nearly a decade (I used it internally at Google!) and have really admired Craig's work on it.

big news for me: after 5000+ days and too many excellent colleagues to mention, I'm leaving Google.

it's been a fantastic ride, and the hardest part about leaving is saying goodbye to my teammates and colleagues.

Next our series of small monthly updates from the interpretability team, including a few fun things:

1. We use do feature attribution to find features related to specific completions (following the athlete-sport association example of Neel Nanda )

Another small update from us, including some fun results about circuit analysis with SAEs.

We’re hiring for the adversarial robustness team Anthropic!

As an Alignment subteam, we're making a big effort on red-teaming, test-time monitoring, and adversarial training. If you’re interested in these areas, let us know! (emails in 🧵)

I continue to be impressed by the work of Neel's scholars -- very excited to see what the next group will do!

Reflections on Qualitative Research:
transformer-circuits.pub/2024/qualitati…

[h/t to Chris Olah for originating & driving this!]