Sampled-SAE pre-selects a candidate pool of features using batch-level norms or entropy before batch top-K, creating a tunable family that trades reconstruction fidelity for improved probing and reduced absorption on Pythia-160M.
Online row sampling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
extension 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
extension 1polarities
extend 1representative citing papers
citing papers explorer
-
Distribution-Aware Feature Selection for SAEs
Sampled-SAE pre-selects a candidate pool of features using batch-level norms or entropy before batch top-K, creating a tunable family that trades reconstruction fidelity for improved probing and reduced absorption on Pythia-160M.