2 papers
cs.MA2025
Goal-Directedness is in the Eye of the Beholder
Nina Rajcic, Anders Søgaard
Our ability to predict the behavior of complex agents turns on the attribution of goals. Probing for goal-directed behavior comes in two flavors: Behavioral and mechanistic. The fo…
cs.LG2025
Empirical Evaluation of Progressive Coding for Sparse Autoencoders
Hans Peter, Anders Søgaard
Sparse autoencoders (SAEs) \citep{bricken2023monosemanticity,gao2024scalingevaluatingsparseautoencoders} rely on dictionary learning to extract interpretable features from neural n…