Sparse autoencoder analysis of PatchTST FFN activations shows sparse, stable representations with no empirical support for superposition on standard time series forecasting tasks.
Advances in Neural Information Processing Systems (NeurIPS) , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
Sparse autoencoder analysis of PatchTST FFN activations shows sparse, stable representations with no empirical support for superposition on standard time series forecasting tasks.