A small set of sparse autoencoder features in LLMs drives shifts between generous and selfish allocations in dictator games, with causal patching and steering confirming their role and generalization to other social games.
, author Horowitz, J
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
econ.GN 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Understanding the Mechanism of Altruism in Large Language Models
A small set of sparse autoencoder features in LLMs drives shifts between generous and selfish allocations in dictator games, with causal patching and steering confirming their role and generalization to other social games.