Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Abstractive Red-Teaming of Language Model Character
Nate Rahn, Allison Qi, Avery Griffin +3
We want language model assistants to conform to a character specification, which asserts how the model should act across diverse user interactions. While models typically follow th…
cs.LG2024
The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks
Lucius Bushnaq, Stefan Heimersheim, Nicholas Goldowsky-Dill +7
Mechanistic interpretability aims to understand the behavior of neural networks by reverse-engineering their internal computations. However, current methods struggle to find clear…