4 citations · 4 across the 2 of their papers we have counts for
3 papers
q-bio.NC2026
Letting the neural code speak: Automated characterization of monkey visual neurons through human language
Vedang Lad, Katrin Franke, Tamar Rott Shaham +4
Understanding what individual neurons encode is a core question in neuroscience. In primary visual cortex (V1), mathematical models (e.g., Gabor functions) capture neural selectivi…
cs.LG2024
The Remarkable Robustness of LLMs: Stages of Inference?
Vedang Lad, Jin Hwa Lee, Wes Gurnee +1
We investigate the robustness of Large Language Models (LLMs) to structural interventions by deleting and swapping adjacent layers during inference. Surprisingly, models retain 72-…
cs.LG2024★ 4 cited
Opening the AI black box: program synthesis via mechanistic interpretability
Eric J. Michaud, Isaac Liao, Vedang Lad +7
We present MIPS, a novel method for program synthesis based on automated mechanistic interpretability of neural networks trained to perform the desired task, auto-distilling the le…