13 citations · 27 across the 13 of their papers we have counts for
6 papers · 1 filter
Tracing the Thought of a Grandmaster-level Chess-Playing Transformer
Rui Lin, Zhenyu Jin, Guancheng Zhou +7
While modern transformer neural networks achieve grandmaster-level performance in chess and other reasoning tasks, their internal computation process remains largely opaque. Focusi…
Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary Learning
Junxuan Wang, Xuyang Ge, Wentao Shu +2
Transformer architectures, and their attention mechanisms in particular, form the foundation of modern large language models. While transformer models are widely believed to operat…
Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition
Zhengfu He, Junxuan Wang, Rui Lin +5
We propose Low-Rank Sparse Attention (Lorsa), a sparse replacement model of Transformer attention layers to disentangle original Multi Head Self Attention (MHSA) into individually…
Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders
Zhengfu He, Wentao Shu, Xuyang Ge +9
Sparse Autoencoders (SAEs) have emerged as a powerful unsupervised method for extracting sparse representations from language models, yet scalable training remains a significant ch…
Automatically Identifying Local and Global Circuits with Linear Computation Graphs
Xuyang Ge, Fukang Zhu, Wentao Shu +3
Circuit analysis of any certain model behavior is a central task in mechanistic interpretability. We introduce our circuit discovery pipeline with Sparse Autoencoders (SAEs) and a…
Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT
Zhengfu He, Xuyang Ge, Qiong Tang +3
Sparse dictionary learning has been a rapidly growing technique in mechanistic interpretability to attack superposition and extract more human-understandable features from model ac…