alignmentforum.orgwriteupWorkspaceBench: Evaluating Interpretability Methods for the Global Workspace
WorkspaceBench is a benchmark introduced by camilablank, agam_bhatia, Euan Ong and Neel Nanda through the MATS Program for evaluating interpretability methods applied to Global Workspace style neural network architectures. The fetched page only exposed metadata without the article body so specific tasks and metrics could not be confirmed from the text, but the title and venue indicate a mechanistic interpretability evaluation framework.
TL;DR A MATS Program benchmark for evaluating interpretability methods on Global Workspace architectures.
Organisations named here
- AI Alignment Forum
- agam_bhatia
- camilablank
- Euan Ong
- MATS Program
- Neel Nanda
Technologies named here
- WorkspaceBench
Related in ai-safety
alignment.openai.comwriteup