MATS Fellow:
Antoine Vigouroux
Authors:
Antoine Vigouroux, Lee Sharkey
Citations
Abstract:
Parameter decomposition (PD) decomposes neural networks into interpretable computational components that faithfully reflect the original network's operations. However, scaling PD to large models requires vast compute, making it a costly and risky endeavor. Here we propose targeted PD (tPD), which identifies only the components that process specific inputs of interest -- from isolated prompts to large subtasks -- by introducing a high-rank catch-all component that handles all non-target data. We validate tPD on toy models and on transformer language models trained on The Pile, where it recovers reproducible, mechanistically faithful circuits. We extract a CSS-only submodel of a 4-block transformer using 7% of the FLOPs of its published decomposition, and in a 12-block transformer we surgically ablate and rewire memorized sequences, with negligible side effects on other inputs.
HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure
Authors:
Huy Nghiem
Date:
December 8, 2026
Citations:
Uncovering Hidden Propensities in Language Models via Limited-Parameter Finetuning
Authors:
Boyd Kane, Jo Jiao, Elizabeth Donoway, Alex Cloud
Date:
December 7, 2026
Citations:
The MATS Program is an independent research and educational initiative connecting emerging researchers with mentors in AI alignment, governance, and security.
Each MATS cohort runs for 12 weeks in Berkeley, California, followed by an optional 6–12 month extension in London for selected scholars.