Scholay

学术搜索 · AI 审稿 · LaTeX 协作

M. Wattenberg

发表论文 189 篇 · 总被引 44009 次 · h-index 68

代表论文

  • Inference-Time Intervention: Eliciting Truthful Answers from a Language Model (2023 · Neural Information Processing Systems · 被引 1383)
  • Toy Models of Superposition (2022 · arXiv.org · 被引 1004)
  • The What-If Tool: Interactive Probing of Machine Learning Models (2019 · IEEE Transactions on Visualization and Computer Graphics · 被引 607)
  • Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task (2022 · International Conference on Learning Representations · 被引 525)
  • Linearity of Relation Decoding in Transformer Language Models (2023 · International Conference on Learning Representations · 被引 205)
  • AttentionViz: A Global View of Transformer Attention (2023 · IEEE Transactions on Visualization and Computer Graphics · 被引 114)