Title to be confirmed

Add to your list(s) Download to your calendar using vCal

• Arthur Conmy (Google DeepMind)
• Friday 09 May 2025, 12:00-13:00
• Room FW26 with Hybrid Format. Here is the Zoom link for those that wish to join online: https://cam-ac-uk.zoom.us/j/4751389294?pwd=Z2ZOSDk0eG1wZldVWG1GVVhrTzFIZz09.

If you have a question about this talk, please contact Suchir Salhan.

The goal of Mechanistic Interpretability research is to explain how neural networks compute outputs in terms of their internal components. But how much progress has been made towards this goal? While a large amount of Mechanistic Interpretability research has been produced by academia, frontier AI companies such as Google DeepMind and independent researchers in recent years, there are still large open problems in the field. In this talk, I will begin by discussing some background hypotheses and techniques in Mechanistic Interpretability, such as the Linear Representation Hypothesis and common causal interventions. Then, I’ll discuss how this connects to research we’ve done at Google DeepMind in the past year, such as open sourcing Gemma Scope, the most comprehensive set of Sparse Autoencoders, which took over 20% of the compute used to train GPT -3. Finally, I’ll reflect on current priorities and disagreements in Mechanistic Interpretability, several of which are built from Gemma Scope. In short, Mechanistic Interpretability is able to uncover factors influencing model behavior that cannot naively be inferred from prompts and outputs via circuits research, but Mechanistic Interpretability has thus far underperformed when benchmarked on well-defined real-world tasks (such as probing for harmful intent in user prompts).

Arthur Conmy is a Senior Research Engineer at Google DeepMind who works on the Mechanistic Interpretability team.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Computer Education Research
• Computing Education Research
• Department of Computer Science and Technology talks and seminars
• Graduate-Seminars
• Guy Emerson's list
• Interested Talks
• Language Sciences for Graduate Students
• NLIP Seminar Series
• PMRFPS's
• Room FW26 with Hybrid Format. Here is the Zoom link for those that wish to join online: https://cam-ac-uk.zoom.us/j/4751389294?pwd=Z2ZOSDk0eG1wZldVWG1GVVhrTzFIZz09
• Simon Baker's List
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.