AI ALIGNMENT FORUMTags
AF

Transformer Circuits

•

Applied to Addendum: More Efficient FFNs via Attention by Robert_AIZI at 2d

•

Applied to No Really, Attention is ALL You Need - Attention can do feedforward networks by Robert_AIZI at 8d

•

Applied to Tracr: Compiled Transformers as a Laboratory for Interpretability | DeepMind by Cinera Verinia at 1mo

•

Applied to 200 Concrete Open Problems in Mechanistic Interpretability: Introduction by Neel Nanda at 1mo

•

Applied to 200 COP in MI: Techniques, Tooling and Automation by Neel Nanda at 1mo

•

Applied to 200 COP in MI: Analysing Training Dynamics by Neel Nanda at 1mo

•

Applied to 200 COP in MI: Exploring Polysemanticity and Superposition by Neel Nanda at 1mo

•

Applied to 200 COP in MI: Interpreting Algorithmic Problems by Neel Nanda at 1mo

•

Applied to 200 COP in MI: Looking for Circuits in the Wild by Neel Nanda at 1mo

•

Applied to A Walkthrough of In-Context Learning and Induction Heads (w/ Charles Frye) Part 1 of 2 by Neel Nanda at 3mo

•

Applied to A Walkthrough of Interpretability in the Wild (w/ authors Kevin Wang, Arthur Conmy & Alexandre Variengien) by Neel Nanda at 3mo

•

Applied to Anthropic's SoLU (Softmax Linear Unit) by Joel Burget at 7mo

•

Applied to Understanding the tensor product formulation in Transformer Circuits by Ruben Bloom at 1y

•

Created by Ruben Bloom at 1y