2026-09-01

• bookmark goodfire.com · 6 min A Geometric Calculator Inside a Neural Network

2026-08-31

• bookmark distill.pub · 1 min Curve Circuits computer vision

2026-05-28

• bookmark goodfire.ai · 5 min A Geometric Calculator Inside a Neural Network

2026-05-06

• bookmark etale.site · 6 min ,...] algebraic topology

2026-01-282

• bookmark livgorton.com · 1 min Favourite Papers of 2025
• bookmark livgorton.com · 16 min What Would Non-Linear Features Actually Look Like?

2025-08-19

• bookmark tylercosgrove.com · 4 min Do LLMs Have Good Music Taste? evaluationaesthetics

2025-07-23

• bookmark alignment.anthropic.com · 1 min Subliminal Learning: Language Models Transmit Behavioral Traits via Hidden Signals in Data

2025-07-2213

• video youtube.com · 22:42 How might LLMs store facts | Deep Learning Chapter 7 attention mechanisms
• video youtube.com · 1:10:34 Normalization models of attention learning
• video youtube.com · 28:05 How difficult is AI alignment? | Anthropic Research Salon ethicsethics
• video youtube.com · 21:31 ARC-AGI-2 Overview With Francois Chollet
• video youtube.com · 59:25 Causal Representation Learning: A Natural Fit for Mechanistic Interpretability embeddings
• video youtube.com · 1:34:22 How To Think About Thinking Models
• video youtube.com · 56:26 On the Biology of a Large Language Model (Part 2)
• video youtube.com · 2:34:23 Neel Does Research (Vibe Coding Edition)
• video youtube.com · 1:18:13 Information Theory for Language Models: Jack Morris information theory
• video youtube.com · 2 min All the neurons of a neural network learning the sine function : network with 1 neuron per layer
• video youtube.com · 1 min I Visualised Attention in Transformers attention mechanisms
• video youtube.com · 59:05 Navigating Progress in AI and Neuroscience
• video youtube.com · 3:13:13 Sholto Douglas & Trenton Bricken - How LLMs Actually Think

2025-06-26

• bookmark distill.pub · 17 min Activation Atlas

2025-05-16

• bookmark lesswrong.com · 19 min Transformers Represent Belief State Geometry in their Residual Stream

2025-05-04

• bookmark ludwigabap.com · 50 min Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?

2025-04-222

• bookmark transformer-circuits.pub · 3h 34m On the Biology of a Large Language Model efficiency
• bookmark arxiv.org · 1 min Do Llamas Work in English? On the Latent Language of Multilingual Transformers efficiency

2025-04-07

• bookmark lesswrong.com · 11 min Recent AI model progress feels mostly like efficiency

2025-03-29

• bookmark transformer-circuits.pub · 3h 43m Circuit Tracing: Revealing Computational Graphs in Language Models efficiency

2025-03-17

• bookmark physics.allen-zhu.com · 4 min Physics of language models efficiency

2025-03-093

• bookmark colah.github.io · 15 min Neural Networks, Manifolds, and Topology
• bookmark arxiv.org · 1 min (How) Do Language Models Track State?
• bookmark k-a.in · 10 min Why Attention Is All You NeedWhy Attention Is All You Need attention mechanisms

2024-07-29

• bookmark arxiv.org · 1h 2m Cramming: Training a Language Model on a Single GPU in One Day efficiency

2024-07-223

• bookmark adamkarvonen.github.io · 17 min Chess-GPT's Internal World Model
• bookmark arxiv.org · 1 min Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models
• bookmark adamkarvonen.github.io · 15 min Manipulating Chess-GPT's World Model game ai

2024-06-11

• bookmark tinkerd.net · 13 min Multi-Query & Grouped-Query Attention inference caching

2024-05-25

• bookmark fritz.ai · 8 min Heatmaps and CNNs Using Fast.ai

2024-05-013

• bookmark arxiv.org · 1 min Sparse Autoencoders Find Highly Interpretable Features in Language Models efficiency
• bookmark arxiv.org · 1h 25m KAN: Kolmogorov–Arnold Networks
• bookmark arxiv.org · 1h 43m KAN: Kolmogorov-Arnold Networks

2024-03-06

• bookmark medium.com · 13 min The Art of Embeddings: Transforming Text for Vector Databases (Part 2) embeddings

2024-02-16

• bookmark distill.pub · 9 min How to Use t-SNE Effectively statistics

2024-02-09

• bookmark ludwigabap.com · 57 min Memory in Plain Sight: A Survey of the Uncanny Resemblances between Diffusion Models and Associative Memories diffusion

2024-01-28

• bookmark arxiv.org · 1 min Measuring Faithfulness in Chain-of-Thought Reasoning efficiency

2024-01-10

• bookmark chats-lab.github.io · 6 min This project is about how to systematically persuade LLMs to jailbreak them. efficiency

2024-01-05

• bookmark jaykmody.com · 44 min GPT in 60 Lines of NumPy