Methodological Choices, Not Model Differences, Drive Variance in Sparse Autoencoder Interpretability Scores
A new arXiv preprint finds that the variance in autointerpretability scores for sparse autoencoders (SAEs) is dominated by methodological choices in the evaluation pipeline—such as the language model explainer and scoring metric—rather than by differences in SAE architectures themselves. The study shows that commonly used metrics and feature rankings are unstable across different pipeline configurations, raising concerns about the reliability of cross-paper comparisons in this area.
Why it matters: This result calls into question the validity of using current autointerpretability benchmarks to compare interpretability methods, highlighting the need for more standardized evaluation practices in mechanistic interpretability research.
Full story at: arXiv Machine Learning ↗