Hacker News
- Reflections on Qualitative Research https://transformer-circuits.pub/2024/qualitative-essay/index.html 3 comments
- Towards Monosemanticity: Decomposing Language Models with Dictionary Learning https://transformer-circuits.pub/2023/monosemantic-features/index.html 5 comments
- Toy Models of Superposition (2022) https://transformer-circuits.pub/2022/toy_model/index.html 4 comments
- Superposition, Memorization, and Double Descent https://transformer-circuits.pub/2023/toy-double-descent/index.html 7 comments
- Can we reverse engineer transformer models into human-understandable programs? https://transformer-circuits.pub/ 4 comments
- [R] A Mathematical Framework for Transformer Circuits https://transformer-circuits.pub/2021/framework/index.html 8 comments machinelearning
Linking pages
- Transformers for software engineers - Made of Bugs https://blog.nelhage.com/post/transformers-for-software-engineers/ 20 comments
- At the Intersection of LLMs and Kernels - Research Roundup https://charlesfrye.github.io/programming/2023/11/10/llms-systems.html 4 comments
- Nintil - Images and Words: AI in 2026 https://nintil.com/interesting-ai-models 1 comment
- Anthropic \ Tracing Model Outputs to the Training Data https://www.anthropic.com/index/influence-functions 0 comments