- [R] A Mathematical Framework for Transformer Circuits https://transformer-circuits.pub/2021/framework/index.html 8 comments machinelearning
Linking pages
- Manipulating Chess-GPT’s World Model | Adam Karvonen https://adamkarvonen.github.io/machine_learning/2024/03/20/chess-gpt-interventions.html 36 comments
- Anthropic | Core Views on AI Safety: When, Why, What, and How https://www.anthropic.com/index/core-views-on-ai-safety 21 comments
- Transformers for software engineers - Made of Bugs https://blog.nelhage.com/post/transformers-for-software-engineers/ 20 comments
- Sholto Douglas & Trenton Bricken - How to Build & Understand GPT-7's Mind https://www.dwarkeshpatel.com/p/sholto-douglas-trenton-bricken 3 comments
- A Conceptual Guide to Transformers - by Ben Levinstein https://benlevinstein.substack.com/p/a-conceptual-guide-to-transformers 1 comment
- What makes transformers unreasonably effective? https://crypticsilicon.substack.com/p/what-makes-transformers-unreasonably 1 comment
- Do Androids Know Theyâre Only Dreaming of Electric Sheep? https://browse.arxiv.org/html/2312.17249v1 1 comment
- A primer on sparse autoencoders - by Nick Jiang https://nickjiang.substack.com/p/a-primer-on-sparse-autoencoders 1 comment
- Talking About Large Language Models – arXiv Vanity https://www.arxiv-vanity.com/papers/2212.03551/ 0 comments
- DeepMind Open-Sources AI Interpretability Research Tool Tracr https://www.infoq.com/news/2023/02/deepmind-tracr/ 0 comments
- How and Why Transformer Models Transformed NLP - Deepgram Blog ⚡️ https://blog.deepgram.com/capturing-attention-decoding-the-success-of-transformer-models-in-natural-language-processing/ 0 comments
- How does GPT-3 spend its 175B parameters? - by Robert Huben https://aizi.substack.com/p/how-does-gpt-3-spend-its-175b-parameters 0 comments
- In-Context Learning, In Context https://thegradient.pub/in-context-learning-in-context/ 0 comments
- Truth https://compphil.github.io/truth/ 0 comments
- GitHub - elicit/machine-learning-list https://github.com/elicit/machine-learning-list 0 comments
- Positional Encoding for Self Attention - SWE to ML Engineer https://swe-to-mle.pages.dev/posts/positional-encoding-for-self-attention/ 0 comments
- Decoding Complexity with Transformers: Researchers from Anthropic Propose a Novel Mathematical Framework for Simplifying Transformer Models - MarkTechPost https://www.marktechpost.com/2024/05/15/decoding-complexity-with-transformers-researchers-from-anthropic-propose-a-novel-mathematical-framework-for-simplifying-transformer-models/ 0 comments
- GitHub - parasdahal/transformers-from-scratch: Understand how Transformer models are implemented from scratch. https://github.com/parasdahal/transformers-from-scratch 0 comments
- The engineering challenges of scaling interpretability \ Anthropic https://www.anthropic.com/research/engineering-challenges-interpretability 0 comments
Would you like to stay up to date with Computer science? Checkout Computer science
Weekly.
Related searches:
Search whole site: site:transformer-circuits.pub
Search title: A Mathematical Framework for Transformer Circuits
See how to search.