Activation outliers quantified by γ = ||μ||/||σ|| cause feature death in SAEs via initialization shifts; mean-centering eliminates it.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders
Activation outliers quantified by γ = ||μ||/||σ|| cause feature death in SAEs via initialization shifts; mean-centering eliminates it.