5 citations · 6 across the 5 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Closed Gates Leak: Decomposing Adjacent-Layer Cancellation in Gated Language Models
Harvey Dam, Ganesh Gopalakrishnan
In transformer language models with gated multilayer perceptrons (MLPs), adjacent layers write partly against each other into the residual stream. Previous work interpreted this ca…
cs.CR2026
First Attack, Final Offensive: The Dark Forest on an Open Roster
Harvey Dam
The Dark Forest argument holds that a civilization that detects another should strike it at once. Existing formal models make the detected civilization the object of the strike and…