#llm-interpretability Repositories
Discover 9 active open source GitHub repositories tagged with #llm-interpretability, accumulating 16,569 total stars (averaging 1,841 stars per project). Leading this topic is openai/transformer-debugger with 4,123 stars.
9 repositories total
Implements harmful/harmless refusal removal using pure HF Transformers
LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo
[ACL 2025 Demo] Repository for the demo and paper: ReasonGraph: Visualisation of Reasoning Paths
Frequently Asked Questions
What is the most popular #llm-interpretability repository on GitHub?
The top ranked open source #llm-interpretability project on GitHub is openai/transformer-debugger with 4,123 stars.
Which programming languages are most used in #llm-interpretability repositories?
Among the top ranked #llm-interpretability projects on GitHub, the most common programming languages are Python, Jupyter Notebook, HTML.
How is the #llm-interpretability repository ranking calculated?
We track 9 active open source repositories tagged with #llm-interpretability (500+ stars), totaling 16,569 stars with an average of 1,841 stars per repository. Rankings update daily from the GitHub API.