About Blank / Research
  • Overview
  • Recent
  • Areas
  • Landscape
  • Favorites
  • Pipeline
Papers
  • Papers
  • Chapters
  • Triage
  • Review queue
  • Top cited
  • All references
Knowledge graph
  • Frameworks
  • Concepts
  • Methods
  • Findings
  • Claims
  • Hypotheses
  • Predictions
  • Questions
People & places
  • Thinkers
  • Institutes
  • Venues
Communities & gaps
  • Communities
  • Bridges
  • God nodes
  • Shortest path
  • Knowledge graph
  • Gaps
thinker
active
thinker:leo-gao

Leo Gao

Acknowledged for feedback on drafts.

Authored
1
Introduces
0
Studies
0
Affiliations
0
Cited by
7

Authored papers (1)

  • Scaling and evaluating sparse autoencoders2025
    referenced-only

More papers — OpenAlex / S2

Their work is cited by (7)

  • SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability1× refs
  • Persona Features Control Emergent Misalignment1× refs
  • Understanding sparse autoencoder scaling in the presence of feature manifolds1× refs
  • Do Sparse Autoencoders Capture Concept Manifolds?1× refs
  • Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior1× refs
  • Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds1× refs
  • Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution1× refs
Other inbound relations (1)
  • mentionsUnderstanding and Steering Llama 3 with Sparse Autoencoders - Goodfire(paper)

Recent mentions (2)

  • papers-typed
    understanding-steering-8b85ff.md
  • papers
    simulators.md