72 citations · 98 across the 14 of their papers we have counts for
16 papers
Sycophancy Towards Researchers Drives Performative Misalignment
David D. Baek, Xinnuo Li, Anay Gupta +4
The increasing situational awareness of language models raises safety concerns: models might be aware when they are evaluated, and adjust their behavior to evade monitoring and res…
A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
Usman Anwar, Julianna Piskorz, David D. Baek +6
Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms. Yet principled methods to de…
The Singapore Consensus on Global AI Safety Research Priorities
Yoshua Bengio, Tegan Maharaj, Luke Ong +84
Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to ensure that AI is safe, i.e., trustworthy,…
Dense SAE Latents Are Features, Not Bugs
Xiaoqing Sun, Alessandro Stolfo, Joshua Engels +4
Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that…
Scaling Laws For Scalable Oversight
Joshua Engels, David D. Baek, Subhash Kantamneni +1
Scalable oversight, the process by which weaker AI systems supervise stronger ones, has been proposed as a key strategy to control future superintelligent systems. However, it is s…
Towards Understanding Distilled Reasoning Models: A Representational Approach
David D. Baek, Max Tegmark
In this paper, we investigate how model distillation impacts the development of reasoning features in large language models (LLMs). To explore this, we train a crosscoder on Qwen-s…
Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
Subhash Kantamneni, Joshua Engels, Senthooran Rajamanoharan +2
Sparse autoencoders (SAEs) are a popular method for interpreting concepts represented in large language model (LLM) activations. However, there is a lack of evidence regarding the…
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…
Low-Rank Adapting Models for Sparse Autoencoders
Matthew Chen, Joshua Engels, Max Tegmark
Sparse autoencoders (SAEs) decompose language model representations into a sparse set of linear latent vectors. Recent works have improved SAEs using language model gradients, but…
The Geometry of Concepts: Sparse Autoencoder Feature Structure
Yuxiao Li, Eric J. Michaud, David D. Baek +3
Sparse autoencoders have recently produced dictionaries of high-dimensional vectors corresponding to the universe of concepts represented by large language models. We find that thi…
Decomposing The Dark Matter of Sparse Autoencoders
Joshua Engels, Logan Riggs, Max Tegmark
Sparse autoencoders (SAEs) are a promising technique for decomposing language model activations into interpretable linear features. However, current SAEs fall short of completely e…
Investigating Representation Universality: Case Study on Genealogical Representations
David D. Baek, Yuxiao Li, Max Tegmark
Motivated by interpretability and reliability, we investigate whether large language models (LLMs) deploy universal geometric structures to encode discrete, graph-structured knowle…
Efficient Dictionary Learning with Switch Sparse Autoencoders
Anish Mudide, Joshua Engels, Eric J. Michaud +2
Sparse autoencoders (SAEs) are a recent technique for decomposing neural network activations into human-interpretable features. However, in order for SAEs to identify all features…
DafnyBench: A Benchmark for Formal Software Verification
Chloe Loughridge, Qinyi Sun, Seth Ahrenbach +7
We introduce DafnyBench, the largest benchmark of its kind for training and evaluating machine learning systems for formal software verification. We test the ability of LLMs such a…
Black-Box Access is Insufficient for Rigorous AI Audits
Stephen Casper, Carson Ezell, Charlotte Siegmann +18
External audits of AI systems are increasingly recognized as a key mechanism for AI governance. The effectiveness of an audit, however, depends on the degree of access granted to a…
Divide-and-Conquer Dynamics in AI-Driven Disempowerment
Peter S. Park, Max Tegmark
AI companies are attempting to create AI systems that outperform humans at most economically valuable work. Current AI models are already automating away the livelihoods of some ar…