Hacker News with Generative AI: Interpretability

An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability (adamkarvonen.github.io)
Sparse Autoencoders (SAEs) have recently become popular for interpretability of machine learning models (although sparse dictionary learning has been around since 1997). Machine learning models and LLMs are becoming more powerful and useful, but they are still black boxes, and we don’t understand how they do the things that they are capable of. It seems like it would be useful if we could understand how they work.
Machine Learning, Interpretability, Artificial Intelligence
110 points by sebg 50 days ago | 3 comments
A Non-Technical Guide to Interpreting SHAP Analyses (aidancooper.co.uk)
With interpretability becoming an increasingly important requirement for machine learning projects, there's a growing need to communicate the complex outputs of model interpretation techniques to non-technical stakeholders.
Machine Learning, Interpretability, Data Science, Non-technical
14 points by reqo 54 days ago | 0 comments
PiML: Python Interpretable Machine Learning Toolbox (github.com/SelfExplainML)
PiML (or π-ML, /ˈpaɪ·ˈem·ˈel/) is a new Python toolbox for interpretable machine learning model development and validation.
Machine Learning, Python, Open Source, Tools, Interpretability
97 points by skadamat 74 days ago | 20 comments
Interpreting Clip with Sparse Linear Concept Embeddings (SpLiCE) (arxiv.org)
CLIP embeddings have demonstrated remarkable performance across a wide range of computer vision tasks. However, these high-dimensional, dense vector representations are not easily interpretable, restricting their usefulness in downstream applications that require transparency.
Computer Vision, Machine Learning, Embeddings, Interpretability, Artificial Intelligence
7 points by fzliu 106 days ago | 0 comments
Light Recurrent Unit: An Interpretable RNN for Modeling Long-Range Dependency (mdpi.com)
Long-Range Dependencies, Interpretability, Machine Learning, Deep Learning
7 points by PaulHoule 145 days ago | 0 comments
Steering Characters with Interpretability (dmodel.ai)
AI, Machine Learning, Interpretability, Language Models
23 points by atondwal 156 days ago | 3 comments
A Multimodal Automated Interpretability Agent (arxiv.org)
Artificial Intelligence, Machine Learning, Interpretability
83 points by el_duderino 178 days ago | 7 comments
Logit Prisms: Decomposing Transformer Outputs for Mechanistic Interpretability (neuralblog.github.io)
Machine Learning, Interpretability, Transformers
49 points by xcodevn 215 days ago | 8 comments