565 citations · 596 across the 4 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Interpreting Language Model Parameters
Lucius Bushnaq, Dan Braun, Oliver Clive-Griffin +5
Mechanistic interpretability aims to uncover how neural networks use their parameters to implement their impressive neural algorithms. Although previous work has uncovered substant…
stat.ML2026
Towards a mathematical theory of superposition
Michael I. Ivanitskiy, John Jasper, Emily J. King +1
We develop a mathematical theory of superposition in neural networks using tools from frame theory and compressed sensing. In our model, a sparse binary vector \(x\) of active feat…