Characterizing stable regions in the residual stream of LLMs
원문 초록
We identify stable regions in the residual stream of Transformers, where the model's output remains insensitive to small activation changes, but exhibits high sensitivity at region boundaries. These regions emerge during training and become more defined as training progresses or model size increases. The regions appear to be much larger than previously studied polytopes. Our analysis suggests that these stable regions align with semantic distinctions, where similar prompts cluster within regions, and activations from the same region lead to similar next token predictions. This work provides a promising research direction for understanding the complexity of neural networks, shedding light on training dynamics, and advancing interpretability.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Generative Latent Kernel Modeling for Blind Motion Deblurring
Differentially Private Relational Learning with Entity-level Privacy Guarantees
EtiCor++: Towards Understanding Etiquettical Bias in LLMs
Fragility in Average Treatment Effect on the Treated under Limited Covariate Support
Assessing parameter identifiability of a hemodynamics PDE model using spectral surrogates and dimension reduction
ACCESS DENIED INC: The First Benchmark Environment for Sensitivity Awareness
토론
이 논문과 연결된 포럼 글이 아직 없습니다.