Aligned training reparameterizes SAEs to enforce unit alignment between encoder and decoder directions, yielding Pareto gains on SAEBench while removing dead features and improving stability.
Diab, Virginia Smith, and Kun Zhang
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
An audit of SAEBench reveals that Targeted Probe Perturbation and Spurious Correlation Removal metrics fail reliability tests and should not be used to evaluate sparse autoencoders.
citing papers explorer
-
Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)
Aligned training reparameterizes SAEs to enforce unit alignment between encoder and decoder directions, yielding Pareto gains on SAEBench while removing dead features and improving stability.
-
Are Sparse Autoencoder Benchmarks Reliable?
An audit of SAEBench reveals that Targeted Probe Perturbation and Spurious Correlation Removal metrics fail reliability tests and should not be used to evaluate sparse autoencoders.