iiinova — where your digital self keeps evolving

Ian Tenney

@iftenney.bsky.social

183 followers 288 following 3 posts

Staff Research Scientist, People + AI Research (PAIR) team at Google DeepMind. Interpretability, analysis, and visualizations for LLMs. Opinions my own. iftenney.github.io

Posts Replies Media

Reposted by Ian Tenney

Actionable Interpretability Workshop ICML2025 @actinterp.bsky.social · 20/05/2025

🚨 We're looking for more reviewers for the workshop! 📆 Review period: May 24-June 7 If you're passionate about making interpretability useful and want to help shape the conversation, we'd love your input. 💡🔍 Self-nominate here: docs.google.com/forms/d/e/1F...

055

Ian Tenney @iftenney.bsky.social · 06/05/2025

Submission deadline extended to May 19! Working on or have thoughts on real-world applications of interpretability, and how we can use it in practice? Consider submitting to our workshop at ICML 2025. More at actionable-interpretability.github.io and below👇

actionable-interpretability.github.io

General Information

ICML 2025 - Vancouver

001

Ian Tenney @iftenney.bsky.social · 25/04/2025

I'm not at ICLR - but if you are, stop by poster session 3, where @tylerachang.bsky.social is presenting our latest work on training data attribution for LLM pretraining!

030

Ian Tenney @iftenney.bsky.social · 13/12/2024

Check out our new work on scaling training data attribution (TDA) toward LLM pretraining - and some interesting things we found along the way! medium.com/people-ai-re... and more in the thread below from most excellent student researcher @tylerachang.bsky.social

medium.com

Scaling Training Data Attribution

The science of how training data influences LLM behavior

071