papers

Publications (9)

cs.AI2025

Language Models Use Trigonometry to Do Addition

Subhash Kantamneni, Max Tegmark

Mathematical reasoning is an increasingly important indicator of large language model (LLM) capabilities, yet we lack understanding of how LLMs process even simple mathematical tas…

cs.AI2025

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…

cs.LG2025

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…

cs.LG2024

OptPDE: Discovering Novel Integrable Systems via AI-Human Collaboration

Subhash Kantamneni, Ziming Liu, Max Tegmark

Integrable partial differential equation (PDE) systems are of great interest in natural science, but are exceedingly rare and difficult to discover. To solve this, we introduce Opt…

cs.CL2026

Verbalizable Representations Form a Global Workspace in Language Models

Wes Gurnee, Nicholas Sofroniew, Adam Pearce +13

Out of everything the human brain processes, only a small fraction is consciously accessible, in the sense of being available for verbal report, deliberate control, and flexible re…

cs.AI2025

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,…

cs.CL2026

Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers

Adam Karvonen, James Chua, Clément Dumas +8

Large language model (LLM) activations are notoriously difficult to understand, with most existing techniques using complex, specialized methods for interpreting them. Recent work…

nucl-th2023

NuCLR: Nuclear Co-Learned Representations

Ouail Kitouni, Niklas Nolte, Sokratis Trifinopoulos +2

We introduce Nuclear Co-Learned Representations (NuCLR), a deep learning model that predicts various nuclear observables, including binding and decay energies, and nuclear charge r…

cs.LG2024

How Do Transformers "Do" Physics? Investigating the Simple Harmonic Oscillator

Subhash Kantamneni, Ziming Liu, Max Tegmark

How do transformers model physics? Do transformers model systems with interpretable analytical solutions, or do they create "alien physics" that are difficult for humans to deciphe…