A Curated Thread of Visual and Interactive Resources for Learning AI

X user @techNmak published a thread series on "learning AI visually," with a core message: "stop learning AI from static diagrams." Instead of staring at fixed illustrations, hands-on interactive tools let you actually watch a Transformer process text, neural networks train in real time, diffusion unfold step by step—even inspect features inside a real LLM.

Confirmed

• Beginner interactive tools: Georgia Tech Polo Club's Transformer Explainer lets you input any text and watch it flow through GPT-2 (124M parameters) in real time, including tokenization and subsequent computation; TensorFlow Playground lets you adjust datasets, layer counts, neuron counts, activation functions, learning rates, and regularization to intuitively see underfitting, overfitting, and model capacity.
• Classic illustrated guides: Jay Alammar's The Illustrated Transformer remains one of the clearest Transformer explainers, covering embeddings, Q/K/V, multi-head attention, and autoregressive generation; Maarten Grootendorst's "A Visual Guide to Mixture of Experts" breaks down experts and routing mechanisms with 50+ visualizations.
• Intermediate concepts: Abhik Sarkar's interactive concept collection on Transformers & LLMs spans 26 pieces, clarifying terms like RoPE, KV cache, FlashAttention, MQA, GQA, and sliding windows; Sebastian Raschka's guide to attention variants uses diagrams to compare MHA, MQA, GQA, and MLA, explaining why shared key/value heads reduce KV cache memory; Brendan Bycroft's LLM Visualization lets you zoom from model level all the way down to tensor-level operations.
• Systems and inference: Modular's LLM Inference Handbook covers prefill, decode, KV cache, batching, scheduling, quantization, prefix caching, and even speculative decoding.
• Research-grade resources: Google PAIR's AI Explorables includes understanding LLM hidden representations with sparse autoencoders (SAE), the Patchscopes introspection framework, and grokking; Distill is no longer publishing but its archive remains a treasure trove, with standout pieces like How to Use t-SNE Effectively, Feature Visualization, and Activation Atlas.
• Math foundations: 3Blue1Brown teaches linear algebra, neural networks, gradient descent, backpropagation, and attention through geometric intuition.
• Complete roadmap: The author closes with a learning path—math from 3Blue1Brown to Seeing Theory, machine learning from TensorFlow Playground to Distill, then into Transformer and LLM topics, all the way to interpretability tools like Neuronpedia.

Why it matters

LLM-related concepts (KV cache, attention variants, MoE, inference optimization) evolve rapidly and are highly abstract; static diagrams struggle to convey dynamic processes. This collection turns "jargon" into tangible, observable objects, offering learners at every level a layered path from introductory math to research-grade interpretability—a rare, systematic guide to visual AI learning.

2026-09-04 ~ 2026-09-04 · 13 related posts

• Stop learning AI from static diagrams: a thread of the best interactive visual resources — techNmak · 2026-09-04
• [source] Transformer Explainer lets you watch your text flow through GPT-2, token by token — techNmak · 2026-09-04
• Two interactive visualizations take you from GPT-2 tokenization down to tensor-level LLM internals — techNmak · 2026-09-04
• 3Blue1Brown and LLM Visualization: the best ways to build geometric intuition for AI — techNmak · 2026-09-04
• Jay Alammar's Illustrated Transformer remains the cleanest visual explanation of the architecture — techNmak · 2026-09-04
• TensorFlow Playground makes overfitting and model capacity visible as you tweak layers live — techNmak · 2026-09-04
• Google PAIR's AI Explorables: research-grade interactive essays from SAEs to differential privacy — techNmak · 2026-09-04
• Distill is no longer publishing, but its archive remains a goldmine: t-SNE, feature visualization, GNNs — techNmak · 2026-09-04
• 26 interactive visual explainers demystify RoPE, KV cache, FlashAttention and attention sinks — techNmak · 2026-09-04
• Sebastian Raschka's visual guide makes MHA, MQA, GQA and MLA attention variants finally click — techNmak · 2026-09-04
• A visual guide with 50+ diagrams demystifies Mixture of Experts in modern LLMs — techNmak · 2026-09-04
• [source] Modular's LLM Inference Handbook covers prefill, KV cache, batching, quantization and speculative decoding — techNmak · 2026-09-04
• [source] A visual AI learning roadmap: 3Blue1Brown, Transformer Explainer, Neuronpedia and more — techNmak · 2026-09-04