Array-associated reverse transcriptases (ART) are a family of reverse transcriptase (RT) systems in the genomes of jumbo bacteriophages, announced by Anthropic on September 23, 2026 as early results from one…
AI AgentsAI for Science
Attribution graphs are a mechanistic interpretability technique developed by Anthropic that traces the internal "circuits" a large language model uses to turn a specific prompt into a specific output.
Interpretability
Christopher Olah (commonly Chris Olah) is a Canadian machine learning researcher, a co-founder of Anthropic, and the researcher most often credited with founding mechanistic interpretability
InterpretabilityPeople
A crosscoder is a mechanistic interpretability tool, introduced by Anthropic in October 2024, that generalizes the sparse autoencoder (SAE) and the transcoder by learning a single shared dictionary of sparse…
Interpretability
Golden Gate Claude was a temporary, research-oriented public demonstration released by Anthropic on May 23, 2024
Interpretability
On the Biology of a Large Language Model is a mechanistic interpretability paper published by Anthropic on March 27, 2025, in the Transformer Circuits Thread.
AI ResearchInterpretability
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet is the May 21
AI ResearchInterpretability
Towards Monosemanticity is an October 2023 mechanistic interpretability paper from Anthropic that used a sparse autoencoder to decompose the internal activations of a small language model into thousands of…
AI ResearchInterpretability
Toy Models of Superposition is a September 2022 mechanistic interpretability paper from Anthropic that shows how a neural network can represent more features than it has dimensions by packing them into…
AI ResearchInterpretability