#

eraser-metrics

Here is 1 public repository matching this topic...

designer-coderajay / Causally-Grounded-Mechanistic-Interpretability-for-LLMs-with-Faithful-Natural-Language-Explanations

MSc Thesis: Bridging mechanistic interpretability circuits to faithful natural language explanations using ERASER evaluation metrics

msc-thesis explainability gpt-2 natural-language-explanations mechanistic-interpretability transformer-lens eraser-metrics

Updated May 30, 2026
Jupyter Notebook

Improve this page

Add a description, image, and links to the eraser-metrics topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the eraser-metrics topic, visit your repo's landing page and select "manage topics."