English
Related papers

Related papers: How Pruning Reshapes Features: Sparse Autoencoder …

200 papers

Neural Networks can be effectively compressed through pruning, significantly reducing storage and compute demands while maintaining predictive performance. Simple yet effective methods like magnitude pruning remove less important parameters…

Machine Learning · Computer Science 2025-12-03 Max Zimmer , Megi Andoni , Christoph Spiegel , Sebastian Pokutta

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…

Machine Learning · Computer Science 2025-10-13 T. Ed Li , Junyu Ren

Weight pruning is among the most popular approaches for compressing deep convolutional neural networks. Recent work suggests that in a randomly initialized deep neural network, there exist sparse subnetworks that achieve performance…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Vinay Kumar Verma , Nikhil Mehta , Shijing Si , Ricardo Henao , Lawrence Carin

Sparse autoencoders (SAEs) have been widely used for interpretability of neural networks, but their learned features often vary across seeds and hyperparameter settings. We introduce Ordered Sparse Autoencoders (OSAE), which extend…

Machine Learning · Computer Science 2025-12-03 Sophie L. Wang , Alex Quach , Nithin Parsan , John J. Yang

Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large…

Machine Learning · Computer Science 2026-05-19 Michał Brzozowski , Neo Christopher Chung

The rapid advancements in transformer-based language models have revolutionized natural language processing, yet understanding the internal mechanisms of these models remains a significant challenge. This paper explores the application of…

Machine Learning · Computer Science 2025-02-14 Edith Natalia Villegas Garcia , Alessio Ansuini

Sparse autoencoders (SAEs) interpret neural network representations by decomposing activations into sparse combinations of dictionary atoms. However, SAEs assume features combine additively through linear reconstruction, an assumption that…

Machine Learning · Computer Science 2026-05-26 Panagiotis Koromilas , Andreas D. Demou , James Oldfield , Yannis Panagakis , Mihalis Nicolaou

While pruning methods effectively maintain model performance without extra training costs, they often focus solely on preserving crucial connections, overlooking the impact of pruned weights on subsequent fine-tuning or distillation,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Hyeonjin Kim , Jaejun Yoo

State-space language models such as Mamba match Transformer quality while permitting linear complexity inference, yet still comprise billions of parameters that hinder deployment. Existing one-shot pruning methods are tailored to attention…

Machine Learning · Computer Science 2025-06-12 Kaiwen Tuo , Huan Wang

Sparse autoencoders (SAEs) have proven effective for extracting monosemantic features from large language models (LLMs), yet these features are typically identified in isolation. However, broad evidence suggests that LLMs capture the…

Artificial Intelligence · Computer Science 2026-02-13 Yifan Luo , Yang Zhan , Jiedong Jiang , Tianyang Liu , Mingrui Wu , Zhennan Zhou , Bin Dong

Large Language Models (LLMs), such as LLaMA and T5, have shown exceptional performance across various tasks through fine-tuning. Although low-rank adaption (LoRA) has emerged to cheaply fine-tune these LLMs on downstream tasks, their…

Machine Learning · Computer Science 2024-08-08 Mingyang Zhang , Hao Chen , Chunhua Shen , Zhen Yang , Linlin Ou , Xinyi Yu , Bohan Zhuang

Large language models (LLMs) excel in language tasks, especially with supervised fine-tuning after pre-training. However, their substantial memory and computational requirements hinder practical applications. Structural pruning, which…

Machine Learning · Computer Science 2025-01-28 Yijiang Liu , Huanrui Yang , Youxin Chen , Rongyu Zhang , Miao Wang , Yuan Du , Li Du

Model pruning is an essential procedure for building compact and computationally-efficient machine learning models. A key feature of a good pruning algorithm is that it accurately quantifies the relative importance of the model weights.…

Machine Learning · Computer Science 2020-06-22 Mingchen Li , Yahya Sattar , Christos Thrampoulidis , Samet Oymak

Sparse Autoencoders (SAEs) have proven to be powerful tools for interpreting neural networks by decomposing hidden representations into disentangled, interpretable features via sparsity constraints. However, conventional SAEs are…

Automatic speech recognition (ASR) has advanced rapidly in recent years, driven by large-scale pretrained models and end-to-end architectures such as SLAM-ASR. A key component of SLAM-ASR systems is the Whisper speech encoder, which…

Computation and Language · Computer Science 2026-03-31 Ganesh Pavan Kartikeya Bharadwaj Kolluri , Michael Kampouridis , Ravi Shekhar

Model pruning seeks to induce sparsity in a deep neural network's various connection matrices, thereby reducing the number of nonzero-valued parameters in the model. Recent reports (Han et al., 2015; Narang et al., 2017) prune deep networks…

Machine Learning · Statistics 2017-11-15 Michael Zhu , Suyog Gupta

Large Language Models (LLMs) have demonstrated their exceptional performance in various complex code generation tasks. However, their broader adoption is limited by significant computational demands and high resource requirements,…

Machine Learning · Computer Science 2025-01-10 Laura Puccioni , Alireza Farshin , Mariano Scazzariello , Changjie Wang , Marco Chiesa , Dejan Kostic

In this work, we demonstrate that affine mappings between residual streams of language models is a cheap way to effectively transfer represented features between models. We apply this technique to transfer the weights of Sparse Autoencoders…

Computation and Language · Computer Science 2025-11-04 Alan Chen , Jack Merullo , Alessandro Stolfo , Ellie Pavlick

How does scaling the number of parameters in large language models (LLMs) affect their core capabilities? We study two natural scaling techniques -- weight pruning and simply training a smaller or larger model, which we refer to as dense…

Computation and Language · Computer Science 2023-10-10 Tian Jin , Nolan Clement , Xin Dong , Vaishnavh Nagarajan , Michael Carbin , Jonathan Ragan-Kelley , Gintare Karolina Dziugaite

Whisper models have achieved remarkable progress in speech recognition; yet their large size remains a bottleneck for deployment on resource-constrained edge devices. This paper proposes a framework to design fine-tuned variants of Whisper…

Machine Learning · Computer Science 2025-10-15 Prasenjit K Mudi , Anshi Sachan , Dahlia Devapriya , Sheetal Kalyani