3 papers
cs.LG2026
When Does Activation Steering Change What a Model Computes From?
Benjamin Shih, John Winnicki, Eric Darve
Activation steering can reliably change an agent's output by modifying its internal activations. Yet arriving at the same answer need not involve the same computation: behavioral e…
cs.AI2026
Domain-Filtered Knowledge Graphs from Sparse Autoencoder Features
John Winnicki, Abeynaya Gnanasekaran, Eric Darve
Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed…
physics.acc-ph2025
Coincident Learning for Beam-based RF Station Fault Identification Using Phase Information at the SLAC Linac Coherent Light Source
Jia Liang, William Colocho, Franz-Josef Decker +7
Anomalies in radio-frequency (RF) stations can result in unplanned downtime and performance degradation in linear accelerators such as SLAC's Linac Coherent Light Source (LCLS). De…