GPT Circuits – Mapping the inner workings of simple LLMs
I've built an app that extracts interpretable 'circuits' from models using the GPT-2 architecture. These circuits reveal how specific inputs influence the probabilities of the next token in a sequence. While some tutorials present theoretical examples of how feedforward layers and attention heads may produce predictions, this app provides concrete examples of how information flows through an LLM. You can see, for example, the formation of features that search for simple grammatical patterns and trace their construction back to the use of more primitive features. Feel free to reach out with…
GPT Circuits – Mapping the inner workings of simple LLMs launched on October 7, 2024 with 6 votes, #1,611 of 5,185 launches that month and more than 50% of that year's launches. The site was still online in September 2026, 2 years on.
What it does
View interpretable “circuits” extracted from LLMs using the GPT-2 architecture.
In the maker’s words, at launch
I've built an app that extracts interpretable 'circuits' from models using the GPT-2 architecture. These circuits reveal how specific inputs influence the probabilities of the next token in a sequence. While some tutorials present theoretical examples of how feedforward layers and attention heads may produce…
Does a similar job
all alternatives →
Fully client-side GPT2 prediction visualizer2023 · perplexity.vercel.app · ▲153Hi HN! I've found this visualization tool immensely helpful over the years for getting an intuition for how an LLM "sees" some piece of text, and with a bit of elbow grease decided to move all compute to client side so I could make it publicly available. I've found it particularly useful for - Understanding exactly how repetition and patterns affect a small LM's ability to predict correctly - Understanding different tokenization patterns and how it affects model output - Getting a general sense of how "hard" different prediction tasks are for GPT-style models Known problems (that I probably…
I built a tiny LLM to demystify how language models workApr 2026 · github.com · ▲915Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
GPT-4.1 in the API2025 · openai.com · ▲375Announcing GPT-4.1, GPT-4.1 mini, & GPT-4.1 nano in the API
- VIVisual intuitive explanations of LLM concepts (LLM University)2023 · ▲303
Hi HN, We've just published a lot of original, visual, and intuitive explanations of concepts to introduce people to large language models. It's available for free with no sign-up needed and it includes text articles, some video explanations, and code examples/notebooks as well. And we're available to answer your questions in a dedicated Discord channel. You can find it here: https://llm.university/ Having written https://jalammar.github.io/illustrated-transformer/, I've been thinking about these topics and how best to communicate them for half a…
- IGInteractive Graph by LLM (GPT-4o)2024 · columns.ai · ▲45
Data automation and visualization platform for spreadsheet users.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, October 2024
the whole month →
bolt.new▲1,230Build and scale high-performing websites & apps using your words. Join millions and start building today.
AI · 2024 · bolt.new
Softr for Notion▲923Turn Notion databases into portals & apps with no code
Dev tools · 2024 · softr.io
One inbox for all your work discussions
Work · 2024 · generalcollaboration.com