Lee Sharkey

Artificial Intelligence · 2023

A researcher in the Science corpus: 1 paper; trusts 2 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

Whom Lee Sharkey trusts

Their strongest outbound trust, strongest first, inferred from their citations.

  1. Kunihiko Fukushima (in Model Architectures)
  2. Georgios Georgiadis (in Artificial Intelligence)

Papers from Lee Sharkey's perspective

Ordered by how strongly the researchers Lee Sharkey trusts endorse each paper. Same corpus, a different order for every researcher.

  1. Efficient sparse coding algorithms
  2. The Pile: An 800GB Dataset of Diverse Text for Language Modeling
  3. Toy Models of Superposition (arXiv.org)
  4. The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
  5. Investigating Gender Bias in Language Models Using Causal Mediation Analysis
  6. An Overview of Catastrophic AI Risks
  7. Zoom In: An Introduction to Circuits
  8. Adaptively Sparse Transformers
  9. LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
  10. Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small (International Conference on Learning Representations)

Their papers