CE-Bench: A Contrastive Evaluation Benchmark of LLM Interpretability with Sparse Autoencoders
-
Updated
May 18, 2025 - Jupyter Notebook
CE-Bench: A Contrastive Evaluation Benchmark of LLM Interpretability with Sparse Autoencoders
Add a description, image, and links to the contrastive-evaluation topic page so that developers can more easily learn about it.
To associate your repository with the contrastive-evaluation topic, visit your repo's landing page and select "manage topics."