A Quick Tour of the Language Interpretability Tool
The Language Interpretability Tool (LIT) is a modular and extensible tool to interactively analyze and debug a variety of NLP models. LIT brings together common machine learning performance checks with interpretability methods specifically designed for NLP.
A Quick Tour of the Learning Interpretability Tool --> Learning Interpretability Tool Tutorials > Basics > Tour A Quick Tour of the Learning Interpretability Tool Follow along in the hosted demo. The Learning Interpretability Tool (LIT) is a modular and extensible tool to interactively analyze and debug a variety of NLP models. LIT brings together common machine learning performance checks with interpretability methods specifically designed for NLP. Building blocks - modules, groups, and workspaces Modules, groups, and workspaces form the building blocks of LIT. Modules are discrete windows in
saved by
related reading
- Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
- Transformer Explainer: LLM Transformer Model Visually Explainedpoloclub.github.io
- The Building Blocks of Interpretabilitydistill.pub
- interpreting GPT: the logit lens — LessWronglesswrong.com
- nnsightnnsight.net
- LIDA | LIDA: Automated Visualizations with LLMsmicrosoft.github.io
- Prism: mapping interpretable concepts and features in a latent space of language | thesephist.comthesephist.com
- Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activationstransformer-circuits.pub
- An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability | Adam Karvonenadamkarvonen.github.io
- Generalized Language Models | Lil'Loglilianweng.github.io
- LiteRT: Google's next-gen runtime for on-device AItensorflow.org
- Streamlit • A faster way to build and share data appsstreamlit.io