Skip navigation
These are literally the best visual resources for learning how Transformers, LLMs, embeddings…
0:00 / 0:12

These are literally the best visual resources for learning how Transformers, LLMs, embeddings…

Tech with Mak

@techNmak49K followers

Visit on X

61,375 views

These are literally the best visual resources for learning how Transformers, LLMs, embeddings, diffusion, and inference work ↓ 1/ Transformer Explainer - Watch GPT process text through embeddings, attention, MLPs and next-token prediction. 2/ Brendan Bycroft’s LLM Visualization - Explore an LLM from architecture down to tensors and operations. 3/ 3Blue1Brown - Visual intuition for linear algebra, neural networks, backprop, attention and Transformers. 4/ The Illustrated Transformer - One of the clearest visual explanations of embeddings, Q/K/V and attention. 5/ TensorFlow Playground - Watch neural networks learn as you change layers, activations, features and learning rate. 6/ Google PAIR AI Explorables - Interactive explainers on LLMs, generalization, interpretability and model behavior. 7/ Distill - Exceptional visual essays on t-SNE, feature visualization, GNNs and interpretability. 8/ Abhik Sarkar’s Transformer Visualizations - RoPE, KV cache, FlashAttention, MQA, GQA and more. 9/ Visual Guide to Attention Variants - MHA, MQA, GQA and MLA visually compared. 10/ Visual Guide to Mixture of Experts - Routing, experts, sparse activation and load balancing. 11/ Modular LLM Inference Handbook - Prefill, decode, KV cache, batching, quantization and speculative decoding. 12/ Apple Embedding Atlas - Explore clusters, neighborhoods and outliers in large embedding spaces. 13/ Diffusion Explainer - Follow Stable Diffusion step by step. 14/ Neuronpedia - Explore features, activations, SAE latents and attribution graphs inside real models. 15/ Seeing Theory - Probability, Bayes, distributions, regression and inference made interactive. 16/ CNN Explainer - Visualize convolutions, feature maps, activations and pooling. 17/ GAN Lab - Train a GAN in your browser and watch its generated distribution evolve. Save this. There’s a serious AI curriculum hiding inside these links.

Comments

Comments from the original post on X (Twitter)

No comments yet