Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models

Abstract

Sparse Autoencoders (SAEs) are a cornerstone of mechanistic interpretability. Existing training methods inherit the Block Training paradigm from LLM pre-training, which introduces destructive gradient noise in instruct models due to attention leakage from unrelated contexts. Using GSNR analysis, we theoretically characterize this issue and propose $\underline{\textbf{F}}$inetuning-$\underline{\textbf{a}}$ligned $\underline{\textbf{S}}$equential $\underline{\textbf{T}}$raining ($\textit{FAST}$), a sequential training paradigm specifically designed for instruct models. $\textit{FAST}$ aligns SAE training with the data distribution and activation patterns of instruct models, substantially improving both reconstruction fidelity and feature interpretability. Experimental results show that $\textit{FAST}$ achieves higher GSNR, a significantly lower log-scaled MSE of 0.6468 compared to the baseline’s 5.1985, and a near-zero Delta Loss (-0.51\% to 0.37\%). Moreover, on Llama-3.2-3B-it, $\textit{FAST}$ produces 21.1\% high-quality features, substantially outperforming baseline methods that achieve 7.0\% and 10.2\%. We further find that intervening on special token activations through SAEs can improve generation quality, revealing new opportunities for fine-grained control. Our codes are available as open source at https://github.com/Geaming2002/FAST.