assets/example-vault/wiki/index.md
Index — example-vault
Updated 2026-04-10 • 4 pages
Content catalog. Read this first when answering queries. Topic: LLM Interpretability
Synthesis (1)
- [[synthesis/interpretability-overview|Interpretability Overview]] — current thesis on mechanistic interpretability in LLMs (1 source · upd 2026-04-10)
Concept (1)
- [[concepts/sparse-autoencoder|Sparse Autoencoder]] — dictionary-learning method for decomposing polysemantic neurons into monosemantic features (1 source · upd 2026-04-10)
Entity (1)
- [[entities/anthropic|Anthropic]] — AI safety company, developer of Claude; major contributor to interpretability research (1 source · upd 2026-04-10)
Source (1)
- [[sources/monosemanticity|Towards Monosemanticity]] — Anthropic 2024 paper using sparse autoencoders to extract interpretable features from a one-layer transformer (upd 2026-04-10)