Visualizing transformer execution traces: computed values vs copy ops from tape-memory
ctjlewis · x · 2026-09-28
ctjlewis shares an execution-trace visualization that shows the exact tokens written at each step, color-coding each operation slot and how information flows from one token to the next. Solid fills mark computed values; bordered cells are copy operations reading a prior value from tape-memory. The final return statement assembles the O… values collected at the end of each step into one sequence via chained copy operations.
More from Research
- Continual-ARC: lifelong ARC-AGI stream finds agent harness persistence rarely beats simple caching — unifyai · 2026-11-16
- DySENSE: MIT's GenAI framework synthesizes satellite imagery with dynamic city energy maps — MIT · 2026-11-16
- WebArena-Pro: a 300-task multimodal benchmark across 20 self-hosted apps for web agents — McGill-NLP · 2026-11-16
- Training-free page-sparse decode in llama.cpp: 1.72× faster 128k decoding on an RTX 5090 — topppggg · 2026-11-16
- Training Qwen3-8B to drive a simulated hand spawns a dedicated internal 'pressure' direction — repligate · 2026-11-16
- Google Research open-sources PaperOrchestra, a multi-agent framework for writing AI papers — google-research · 2026-11-16