JacobPfau / procgenAISCLinks
☆19Updated 2 years ago
Alternatives and similar repositories for procgenAISC
Users that are interested in procgenAISC are comparing it to the libraries listed below
Sorting:
- Pytorch implementation on OpenAI's Procgen ppo-baseline, built from scratch.☆14Updated last year
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- Interpreting how transformers simulate agents performing RL tasks☆87Updated last year
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- Sparse Autoencoder Training Library☆54Updated 4 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆128Updated 3 years ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆79Updated 3 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated last year
- Measuring the situational awareness of language models☆38Updated last year
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆191Updated 2 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated this week
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- Tools for studying developmental interpretability in neural networks.☆103Updated 2 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
- Sparse and discrete interpretability tool for neural networks☆63Updated last year
- A dataset of alignment research and code to reproduce it☆77Updated 2 years ago
- ☆34Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆19Updated 8 months ago
- Universal Neurons in GPT2 Language Models☆30Updated last year
- A reinforcement learning environment for the IGLU 2022 at NeurIPS☆34Updated 2 years ago
- This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.☆31Updated last year
- Implementation of Direct Preference Optimization☆16Updated 2 years ago
- ☆138Updated last month
- ☆23Updated 9 months ago
- ☆35Updated 2 years ago
- Code repo for the model organisms and convergent directions of EM papers.☆28Updated last month
- ☆27Updated 2 years ago
- ☆23Updated last year
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆19Updated 11 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year