Hugging Face Trending Papers August 13, 2026

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization

Read the original on Hugging Face Trending Papers →

Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features still relies primarily on external observation. This reliance leads to superficial explanations inferred from observed model behavior and computational inefficiency from collecting such behavioral evidence at scale.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

llms

arXiv AI

Jun 26

Discovering Millions of Interpretable Features with Sparse Autoencoders

arXiv:2606. 26620v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a powerful tool for decomposing superposed language model representations into sparse and interpretable features.

By XinYang He, Wei Wang, Bing Zhao, Xuan Ren, WenBo Li, WeiXu Qiao, Hu Wei, Lin Qu

llms efficiency

arXiv Machine Learning

Jun 9

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization

arXiv:2606. 08496v1 Announce Type: cross Abstract: Although Sparse Autoencoders (SAEs) have mitigated the opacity of large language models (LLMs) by decomposing dense representations into sparse features, explaining these features still remains a central challenge.

By Jingyi He, Haiyan Zhao, Ruxue Shi, Yanguang Liu, Xin Wang, Fei Sun, Mengnan Du

llms safety

arXiv Machine Learning

Jun 2

AdaptiveK: Complexity-Driven Sparse Autoencoders for Interpretable Language Model Representations

arXiv:2508. 17320v3 Announce Type: replace Abstract: Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research.

By Yifei Yao, Hanrong Zhang, Mengnan Du

llms efficiency safety

arXiv AI

Jul 21

Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence

arXiv:2607. 17770v1 Announce Type: cross Abstract: Within Explainable Artificial Intelligence, mechanistic interpretability uses Sparse Autoencoders (SAEs) to extract more interpretable features from neural representations.

By Katarzyna Filus, Sebastian Pokuci\'nski

llms rag efficiency multimodal safety

arXiv Machine Learning

Aug 4

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering

arXiv:2604. 03532v2 Announce Type: replace-cross Abstract: Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult.

By Sing Hieng Wong, Hassan Sajjad, A. B. Siddique

llms benchmarks

arXiv AI

Jun 12

Language Model Circuits Are Sparse in the Neuron Basis

arXiv:2601. 22594v2 Announce Type: replace-cross Abstract: The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986).

By Aryaman Arora, Zhengxuan Wu, Jacob Steinhardt, Sarah Schwettmann

llms benchmarks safety

Related stories

Discovering Millions of Interpretable Features with Sparse Autoencoders

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization

AdaptiveK: Complexity-Driven Sparse Autoencoders for Interpretable Language Model Representations

Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering

Language Model Circuits Are Sparse in the Neuron Basis