alan-cooney / transformer-from-scratchLinks
Decoder only transformer, built from scratch with PyTorch
☆31Updated last year
Alternatives and similar repositories for transformer-from-scratch
Users that are interested in transformer-from-scratch are comparing it to the libraries listed below
Sorting:
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆214Updated 8 months ago
- Mechanistic Interpretability Visualizations using React☆282Updated 8 months ago
- ☆335Updated 2 weeks ago
- Sparse Autoencoder for Mechanistic Interpretability☆260Updated last year
- ☆126Updated last year
- ☆238Updated 11 months ago
- Sparsify transformers with SAEs and transcoders☆613Updated last week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆207Updated this week
- ☆165Updated 9 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆646Updated this week
- ☆53Updated 9 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆225Updated 3 weeks ago
- ☆116Updated last month
- Using sparse coding to find distributed representations used by neural networks.☆265Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆121Updated 6 months ago
- ☆185Updated last month
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 10 months ago
- ☆33Updated last year
- Attribution-based Parameter Decomposition☆29Updated 2 months ago
- Open source interpretability artefacts for R1.☆157Updated 4 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆198Updated 9 months ago
- Training Sparse Autoencoders on Language Models☆935Updated this week
- Tools for studying developmental interpretability in neural networks.☆101Updated 2 months ago
- ☆29Updated last year
- ☆141Updated 2 weeks ago
- Steering Llama 2 with Contrastive Activation Addition☆178Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆521Updated 3 weeks ago
- ☆122Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 2 years ago
- METR Task Standard☆159Updated 7 months ago