arXiv Machine Learning By Suchit Gupte, Xueru Zhang, Mohammad Mahdi Khalili

When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs

Read the original on arXiv Machine Learning →

Sparse autoencoders (SAEs) are commonly used to interpret large language models, but their reliability after pruning is unclear. This study shows that pruning’s effect on an SAE is governed by perturbation energy, a covariance-weighted norm, and that magnitude pruning distorts the representation space by ignoring activation geometry. Activation-aware pruning methods such as Wanda and SparseGPT better preserve SAE behavior, and the authors find that middle layers are especially vulnerable, leading them to propose a layer‑wise sparsity allocation that reduces perplexity for a given sparsity level.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Aug 10

The Sparsity Whisperer

arXiv:2608. 06630v1 Announce Type: new Abstract: Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs.

By Linghao Kong, Inimai Subramanian, Micah Adler, Dan Alistarh, Dan Gutfreund, Nir Shavit
arXiv Computation and Language
4d ago

Pruning Laws for Large Language Models

arXiv:2504.04342v2 Announce Type: replace Abstract: Scaling up model parameters and training data consistently improves the performance of large language models (LLMs), but at the cost of rapidly gro...

By Ayan Sengupta, Siddhant Chaudhary, Tanmoy Chakraborty
arXiv AI
Jul 21

Sparsity-Aware Low-Rank Representation for Efficient Fine-Tuning of Large Language Models

arXiv:2601. 16991v3 Announce Type: replace-cross Abstract: Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments.

By Longteng Zhang, Sen Wu, Shuai Hou, Zhengyu Qing, Zhuo Zheng, Danning Ke, Qihong Lin, Qiang Wang, Shaohuai Shi, Xiaowen Chu