Arthur Conmy - Mechanistic Interpretability Research Frontiers

Join us for an exclusive opportunity to hear from Arthur Conmy, a leading interpretability researcher at Google DeepMind, as he shares his research journey in mechanistic interpretability. Arthur will discuss his key insights, notable contributions, and his current work with the MATS program. He’ll also offer valuable advice for beginners in the field, making this a must-attend event for anyone interested in advancing their understanding of interpretability in AI.