Skip to content
Longterm Wiki has not been actively maintained since May 2026. Some data is still updated occasionally, but please don't rely on this site being current or accurate.
Longterm Wiki

Transformer Circuits

Company BlogHigh(4)
Anthropic's interpretability research
Resources
10
Citing pages
15
Tracked domains
1

Credibility Rating

4/5
High(4)
High quality. Established institution or organization with editorial oversight and accountability.

Tracked Domains

transformer-circuits.pub

Resources (10)

10 resources
AuthorsSummary
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnetpaper—S8
Transformer Circuits Threadpaper—S4
Circuits Updates - July 2025web—S3
Anthropic's dictionary learning workweb—S3
A Mathematical Frameworkweb—S2
Towards Monosemanticityweb—S1
In-context Learning and Induction Headsweb—S1
Circuits Updates: July 2024 (Transformer Circuits Thread)web—S1
Introspection Researchweb—S1
circuit tracing researchweb—S1

Citing Pages (15)

AI Accident Risk CruxesAI AlignmentAnthropicAnthropic Core ViewsChris OlahDense TransformersInterpretabilityIs Interpretability Sufficient for Safety?Mechanistic InterpretabilityProbing / Linear ProbesAI Scaling LawsSituational AwarenessSleeper Agent DetectionSparse Autoencoders (SAEs)Technical AI Safety Research
Publication ID: transformer-circuits