progscrape: transformer-circuits.pub

When models manipulate manifolds: The geometry of a counting task

23 days ago transformer-circuits.pub

Emergent Introspective Awareness in Large Language Models

22 days ago transformer-circuits.pub

Visual Features Across Modalities: SVG and ASCII Art Cross-Modal Understanding

27 days ago transformer-circuits.pub art svg

The Biology of a Large Language Model

7 months ago transformer-circuits.pub ai biology

Circuit Tracing: Revealing Computational Graphs in Language Models (Anthropic)

7 months ago transformer-circuits.pub

Toy Models of Superposition (2022)

12 months ago transformer-circuits.pub

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

18 months ago transformer-circuits.pub

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

18 months ago transformer-circuits.pub

Towards Monosemanticity: Decomposing Language Models with Dictionary Learning

2 years ago transformer-circuits.pub

Toy Models of Superposition (2022)

2 years ago transformer-circuits.pub

Toy Models of Superposition

2 years ago transformer-circuits.pub ai

Superposition, Memorization, and Double Descent

2 years ago transformer-circuits.pub