Anton Korznikov, Andrey Galichin, Alexey Dontsov, Oleg Rogov, Ivan Oseledets, Elena Tutubalina
Sparse Autoencoders (SAEs) have emerged as a promising tool for interpreting neural networks by decomposing their activations into sparse sets of human-interpretable features. Recent work has introduced multiple SAE variants and successfully scaled them to frontier models. Despite much excitement, a growing number of negative results in downstream tasks casts doubt on whether SAEs recover meaningful features. To directly investigate this, we perform two complementary evaluations. On a synthetic setup with known ground-truth features, we demonstrate that SAEs recover only $9\%$ of true features despite achieving $71\%$ explained variance, showing that they fail at their core task even when reconstruction is strong. To evaluate SAEs on real activations, we introduce three baselines that constrain SAE feature directions or their activation patterns to random values. Through extensive experiments across multiple SAE architectures, we show that our baselines match fully-trained SAEs in interpretability (0.87 vs 0.90), sparse probing (0.69 vs 0.72), and causal editing (0.73 vs 0.72). Together, these results suggest that SAEs in their current state do not reliably decompose models' internal mechanisms.
Shirin Alanova, Kristina Kazistova, Ekaterina Galaeva, Alina Kostromina, Vladimir Smirnov, Redko Dmitry, Alexey Dontsov, Maxim Zhelnin 等 10 位作者
The demand for efficient large language model inference has spurred interest in sparsification, yet current hardware support remains narrowly focused on 2:4 weight sparsity. In this work, we argue that activation sparsity despite being overlooked in hardware design offers a promising path for dynamic, input-adaptive compression with significant I/O and memory benefits. We present a comprehensive post-training study of N{:}M activation pruning across four LLMs (Llama2-7B-chat, Llama3.1-8B-Instruct, Qwen2.5-7B-Instruct, Gemma3-4B-Instruct), demonstrating that activation pruning consistently outperforms weight pruning at matched sparsity levels. We evaluate lightweight, plug-and-play error mitigation and selection strategies that require minimal or no calibration data across four sparsity patterns: 2:4, 4:8, 8:16, and 16:32. Among these, 16:32 approaches the performance of unstructured 50% sparsity and is is approximately 2.7\times better than 2:4, while 8:16 offers an optimal balance of accuracy and practicality. Our results provide evidence that next-generation accelerators should consider native support for N{:}M activation sparsity and can serve as a strong baseline for the future methods.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表