4764

on the atlas — 23

• [1912.02178] Fantastic Generalization Measures and Where to Find Them1 savers
• Against Interpretability: a Critical Examination of the Interpretability Problem in Machine Learning | Philosophy & Technology | Springer Nature Link1 savers
• The Banal Evil of AI Safety - by Ben Recht - arg min1 savers
• [2502.21212] Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought1 savers
• [2502.04327] Value-Based Deep RL Scales Predictably1 savers
• KL-divergence as an objective function — Graduate Descent1 savers
• Reformist Reinforcement Learning - by Ben Recht - arg min1 savers
• The Mythos of Model Interpretability: In machine learning, the concept of interpretability is both important and slippery.: Queue: Vol 16, No 31 savers
• Sparse Autoencoders Find Highly Interpretable Features in Language Models2 savers
• PaulPauls/llama3_interpretability_sae: A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.1 savers
• pigeon1 savers
• Greenback Bears and Fiscal Hawks: Finance is a Jungle and Text Embeddings Must Adapt - ACL Anthology1 savers
• On Calibration of Modern Neural Networks1 savers
• On Getting Confidence Estimates from Neural Networks | Bharath's notes1 savers
• The N Implementation Details of RLHF with PPO | ICLR Blogposts 20241 savers
• Designing and Interpreting Probes · John Hewitt1 savers
• A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity1 savers
• Understanding Intermediate Layers Using Linear Classifier Probes1 savers
• Confidence Regulation Neurons in Language Models1 savers
• Silicon Valley’s Gold Rush Roots—Asterisk1 savers
• nelsn.jpg1 savers
• When RAND Made Magic in Santa Monica—Asterisk4 savers
• Rethinking High-School Science Fairs—Asterisk8 savers