Transformer Circuits · 实时热榜

lens callout — standalone transformer-circuits.pub

Verbalizable Representations Form a Global Workspace in Language Models transformer-circuits.pub

Circuits Updates – June 2026 transformer-circuits.pub

Circuits Updates – May 2026 transformer-circuits.pub

Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations transformer-circuits.pub

HeadVis: An Interactive Tool For Investigating Attention Heads transformer-circuits.pub

Emotion Concepts and their Function in a Large Language Model transformer-circuits.pub

Circuits Updates – November 2025 transformer-circuits.pub

Emergent Introspective Awareness in Large Language Models transformer-circuits.pub

Circuits Updates – October 2025 transformer-circuits.pub

When Models Manipulate Manifolds: The Geometry of a Counting Task transformer-circuits.pub

Circuits Updates - September 2025 transformer-circuits.pub

Circuits Updates - August 2025 transformer-circuits.pub

A Toy Model of Mechanistic (Un)Faithfulness transformer-circuits.pub

Tracing Attention Computation Through Feature Interactions transformer-circuits.pub

A Toy Model of Interference Weights transformer-circuits.pub

Sparse mixtures of linear transforms transformer-circuits.pub

Circuits Updates - July 2025 transformer-circuits.pub

Circuits Updates - April 2025 transformer-circuits.pub

Progress on Attention transformer-circuits.pub

Attribution Graphs transformer-circuits.pub

Attribution Graph: Human: A 35-year-old woman presents with a severe headache that began this morning while she was at the gym. She describes it as "much worse than my usual headaches" and says it's concentrated at the back of her head. The pain is 8/1 transformer-circuits.pub

Attribution Graph: Fact: the capital of the state containing Dallas is transformer-circuits.pub

Click a feature on the left for details transformer-circuits.pub

Attribution Graph: Human: A 45-year-old man presents with fatigue and mild shortness of breath that's been getting gradually worse over the past month. He's been having trouble keeping up with his regular tennis games and finds himself needing to rest after transformer-circuits.pub

Circuit Tracing: Revealing Computational Graphs in Language Models transformer-circuits.pub

On the Biology of a Large Language Model transformer-circuits.pub

Insights on Crosscoder Model Diffing transformer-circuits.pub

Circuits Updates - January 2025 transformer-circuits.pub

Stage-Wise Model Diffing transformer-circuits.pub