A filtering and dual-graph construction method turns flat SAE feature inventories into domain-specific knowledge graphs that recover textbook structure and enable reasoning audits.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Domain-Filtered Knowledge Graphs from Sparse Autoencoder Features
A filtering and dual-graph construction method turns flat SAE feature inventories into domain-specific knowledge graphs that recover textbook structure and enable reasoning audits.