activity
20232025
most citedA Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations

12 citations · 27 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG20251 cited

Detecting Strategic Deception Using Linear Probes

Nicholas Goldowsky-Dill, Bilal Chughtai, Stefan Heimersheim +1

AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs…

cs.LG20259 cited

Open Problems in Mechanistic Interpretability

Lee Sharkey, Bilal Chughtai, Joshua Batson +26

Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goa…

cs.LG20241 cited

Transformer Circuit Faithfulness Metrics are not Robust

Joseph Miller, Bilal Chughtai, William Saunders

Mechanistic interpretability work attempts to reverse engineer the learned algorithms present inside neural networks. One focus of this work has been to discover 'circuits' -- subg…

cs.CL20242 cited

Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

Rudolf Laine, Bilal Chughtai, Jan Betley +6

AI assistants such as ChatGPT are trained to respond to users by saying, "I am a large language model". This raises questions. Do such models know that they are LLMs and reliably a…

cs.LG20242 cited

Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs

Bilal Chughtai, Alan Cooney, Neel Nanda

How do transformer-based large language models (LLMs) store and retrieve knowledge? We focus on the most basic form of this task -- factual recall, where the model is tasked with e…

cs.LG202312 cited

A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations

Bilal Chughtai, Lawrence Chan, Neel Nanda

Universality is a key hypothesis in mechanistic interpretability -- that different models learn similar features and circuits when trained on similar tasks. In this work, we study…