RT @iatitov: Many thanks to the @ActInterp organisers for highlighting our work - and congratulations to Pedro, Alex and the other awardee….

1⃣Detecting High-Stakes Interactions with Activation Probes - 2⃣ Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations -

Big congrats to Alex McKenzie, Pedro Ferreira, and their collaborators on receiving Outstanding Paper Awards!👏👏 .and thanks for the fantastic oral presentations!. Check out the papers here 👇

RT @ndif_team: Great to present what’s coming next for NDIF at the @actinterp workshop at #ICML2025!. If you missed us, let’s chat after th….

👇🏻.

RT @aryaman2020: maybe I will live tweet the actionable interp workshop panel.

Starting now: our panel on actionable interpretability!.@nsaphra @saprmarks @kylelostat @FazlBarez

Huge thanks to Sarah Schwettmann for a fascinating keynote on "AI Investigators for Understanding AI Systems" 🤖 @cogconfluence @TransluceAI

Grab a ☕️ and join us for a keynote by @RICEric22: Explanations for Experts via Guarantees and Domain Knowledge: From Attributions to Reasoning

➡️ Join us for the keynote by @byron_c_wallace: “What (if anything) can interpretability do for healthcare?”

The second poster session is starting now!🙌🏻

RT @_AKassem: Come see our poster about how to predict side effects of unlearning and Fine-Tuning at @ActInterp

RT @evzen_wy: Crazy amount of cool work concentrated in one room.

The first poster session is happening now!

The one and only @_beenkim on Agentic Interpretability and Neologism: What LLMs Can Offer Us!

We’ve started!👏.Looking forward to an exciting day!💫🔍⚙️

RT @ActInterp: 🚨The Actionable Interpretability Workshop is happening tomorrow at ICML! .Join us for an exciting lineup of speakers, nearl….

🚨The Actionable Interpretability Workshop is happening tomorrow at ICML! .Join us for an exciting lineup of speakers, nearly 70 posters, and a great panel discussion 🙌.Don’t miss it! 🔍⚙️. @icmlconf @ActInterp

RT @iftenney: At ICML? Interested in how we can do more with interpretability to have practical impact on the rest of AI? Come to our works….

RT @_shruti_joshi_: I will be at the Actionable Interpretability Workshop (@ActInterp, #ICML) presenting *SSAEs* in the East Ballroom A fro….