12 citations · 29 across the 13 of their papers we have counts for
13 papers
How Transparent is DiffusionGemma?
Joshua Engels, Callum McDougall, Bilal Chughtai +11
LLM reasoning transparency is a critical affordance for understanding model decisions, mitigating misuse and misalignment, and debugging surprising model behaviors. However, Diffus…
Training on Documents About Monitoring Leads to CoT Obfuscation
Reilly Haskins, Bilal Chughtai, Joshua Engels
Chain-of-thought (CoT) monitoring is one of the most promising tools we have for detecting model misbehavior, but its effectiveness depends on models faithfully externalizing their…
Building Production-Ready Probes For Gemini
János Kramár, Joshua Engels, Zheng Wang +4
Frontier language model capabilities are improving rapidly. We thus need stronger mitigations against bad actors misusing increasingly powerful systems. Prior work has shown that a…
Difficulties with Evaluating a Deception Detector for AIs
Lewis Smith, Bilal Chughtai, Neel Nanda
Building reliable deception detectors for AI systems -- methods that could predict when an AI system is being strategically deceptive without necessarily requiring behavioural evid…
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…
Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
Zora Che, Stephen Casper, Robert Kirk +12
Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluat…
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…
Towards evaluations-based safety cases for AI scheming
Mikita Balesni, Marius Hobbhahn, David Lindner +13
We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through sc…
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…
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…
Can Language Models Explain Their Own Classification Behavior?
Dane Sherburn, Bilal Chughtai, Owain Evans
Large language models (LLMs) perform well at a myriad of tasks, but explaining the processes behind this performance is a challenge. This paper investigates whether LLMs can give f…
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…
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…