Critical percolation clusters embedded in high dimensions, combined with taxonomic latent variables, form an analytically tractable synthetic data model whose ground-truth hierarchy can be linearly decoded from network activations.
Synthsaebench: Evaluating sparse autoencoders on scalable realistic synthetic data
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.LG 4years
2026 4verdicts
UNVERDICTED 4representative 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.
SAEs exhibit a rate-distortion-polysemanticity tradeoff where monosemanticity increases rate and distortion, with optimal polysemanticity set by feature co-occurrence probabilities in the data.
Trains and releases SAEs for Qwen3-1.7B/4B/8B models with layer-wise coverage and demonstrates causal steering of refusal via selected features.
citing papers explorer
-
Critical Percolation as a Synthetic Data Model for Interpretability
Critical percolation clusters embedded in high dimensions, combined with taxonomic latent variables, form an analytically tractable synthetic data model whose ground-truth hierarchy can be linearly decoded from network activations.
-
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.
-
The Rate-Distortion-Polysemanticity Tradeoff in SAEs
SAEs exhibit a rate-distortion-polysemanticity tradeoff where monosemanticity increases rate and distortion, with optimal polysemanticity set by feature co-occurrence probabilities in the data.
-
Discovering Millions of Interpretable Features with Sparse Autoencoders
Trains and releases SAEs for Qwen3-1.7B/4B/8B models with layer-wise coverage and demonstrates causal steering of refusal via selected features.