cross-layer-transcoder
Here are 3 public repositories matching this topic...
A Mechanistic Interpretability Toolkit for Cross-Layer Transcoder Training and Attribution-Graph Visualization
-
Updated
Apr 16, 2026 - Python
Automates attribution-graph analysis via probe prompting: circuit-trace a prompt, auto-generate concept probes, profile feature activations, cluster supernodes.
-
Updated
Jun 5, 2026 - Jupyter Notebook
Cross-Layer Transcoder (CLT) library for extracting sparse interpretable features from transformer models. Batched processing, memory-efficient, works with any LLM/VLM.
-
Updated
Mar 23, 2026 - Python
Improve this page
Add a description, image, and links to the cross-layer-transcoder topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the cross-layer-transcoder topic, visit your repo's landing page and select "manage topics."