26 interactive visual explainers demystify RoPE, KV cache, FlashAttention and attention sinks

techNmak · x · 2026-09-04

A recommended resource: Abhik Sarkar's Transformers & LLMs collection offers 26 interactive visual concept explainers covering RoPE, KV cache, FlashAttention, MQA, GQA, sliding-window attention, attention sinks, plus ViT topics like CLS tokens, hierarchical attention and positional embeddings.

Also featured: the Distill journal archive — no longer publishing but still exceptional, with classics on t-SNE, feature visualization, Activation Atlas and GNNs.

Related event: A Curated Thread of Visual and Interactive Resources for Learning AI(13 posts)→

Original post →

More from Research

Research channel →