Explore Library Roadmaps Create My blogs Pricing

Library

Search the public knowledge base.

Filters

Categories

Machine Learning22 Reinforcement Learning11 Transformers5 LLMs4 Attention3 Diffusion2 AI Interpretability1 BPE1 causal interventions1 context paradigm1 Cordis1 Databases1 Distributed Machine Learning Systems1 Distributed Training1 DTensor1 Dynamic software composition1 energy-based models1 FSDP1 GPU-Parallel Robot Learning1 importance sampling1

Sort by

Latest Most read Recently updated

Library

Search the public knowledge base.

K

Machine Learning Reinforcement Learning Transformers LLMs Attention Diffusion AI Interpretability BPE causal interventions context paradigm

1 results

Sort by

Latest Most read Recently updated

Mechanistic Interpretability: Reverse-Engineering the Algorithms Inside Neural Networks

Take a simple completion: “Alice gave Bob the book because wanted it.” Suppose the model assigns a high target logit $y$ to the corr...

AI Interpretabilitymechanistic interpretabilitytransformer circuits

Sep 8, 2026 19 min read 106