Event-grounded SAE analysis in VLA policies produces stronger causal effects on robot behavior than standard methods by anchoring features to clustered end-effector keyframes across simulations and real-robot tests.
Towards monosemanticity: Decomposing language models with dictionary learning.Transformer Circuits Thread, 2(5):6, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies
Event-grounded SAE analysis in VLA policies produces stronger causal effects on robot behavior than standard methods by anchoring features to clustered end-effector keyframes across simulations and real-robot tests.