LLM

2 articles

Feature Recovery Feature-Learning Fourier-Features Grokking In-Context Learning Interpretability LLM Mechanistic-Interpretability Modular-Addition Sparse Autoencoders Transformers

In-Context Linear Regression Demystified

In-Context Linear Regression Demystified

Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders

Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders