neelnanda-io / GrokkingLinks
A Mechanistic Interpretability Analysis of Grokking
☆23Updated 3 years ago
Alternatives and similar repositories for Grokking
Users that are interested in Grokking are comparing it to the libraries listed below
Sorting:
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆130Updated 3 years ago
- ☆143Updated 2 months ago
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆13Updated 2 years ago
- Sparse Autoencoder Training Library☆55Updated 6 months ago
- ☆62Updated last month
- we got you bro☆36Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆193Updated last year
- 🧠 Starter templates for doing interpretability research☆75Updated 2 years ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆122Updated last year
- ☆117Updated last month
- ☆29Updated last year
- ☆132Updated 2 years ago
- Tools for studying developmental interpretability in neural networks.☆114Updated 4 months ago
- ☆36Updated last year
- ☆24Updated 7 months ago
- ☆27Updated 2 years ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆60Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆227Updated 11 months ago
- ☆17Updated last week
- Open source interpretability artefacts for R1.☆163Updated 7 months ago
- nanoGPT-like codebase for LLM training☆109Updated 2 weeks ago
- ☆53Updated last month
- Steering vectors for transformer language models in Pytorch / Huggingface☆129Updated 8 months ago
- ☆31Updated 7 months ago
- ☆79Updated last month
- Repository with sample code using Apollo's suggested engineering practices☆13Updated 11 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆84Updated 11 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆225Updated last week
- Omnigrok: Grokking Beyond Algorithmic Data☆62Updated 2 years ago