bilal-chughtai / rep-theory-mech-interpLinks
☆27Updated 2 years ago
Alternatives and similar repositories for rep-theory-mech-interp
Users that are interested in rep-theory-mech-interp are comparing it to the libraries listed below
Sorting:
- we got you bro☆36Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- ☆107Updated 8 months ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated last year
- ☆74Updated 2 weeks ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- ☆69Updated 3 years ago
- Attribution-based Parameter Decomposition☆31Updated 4 months ago
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)☆51Updated 3 months ago
- 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
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆40Updated 2 years ago
- ☆29Updated last year
- Universal Neurons in GPT2 Language Models☆30Updated last year
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆19Updated this week
- ☆23Updated 8 months ago
- ☆126Updated last year
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago
- ☆128Updated last year
- ☆110Updated 8 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆82Updated 10 months ago
- ☆22Updated 6 months ago
- ☆15Updated 2 weeks ago
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆23Updated last year
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆79Updated 3 years ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆19Updated last year
- ☆23Updated 10 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Updated 9 months ago
- ☆92Updated last year