alan-cooney / transformer-from-scratchLinks
Decoder only transformer, built from scratch with PyTorch
☆30Updated 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:
- Repository with sample code using Apollo's suggested engineering practices☆9Updated 5 months ago
- Mechanistic Interpretability Visualizations using React☆251Updated 5 months ago
- ☆223Updated 8 months ago
- ☆120Updated 6 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆200Updated 5 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆101Updated 3 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- ☆170Updated last month
- A python sdk for LLM finetuning and inference on runpod infrastructure☆11Updated last week
- ☆97Updated last month
- Sparse Autoencoder for Mechanistic Interpretability☆248Updated 10 months ago
- Attribution-based Parameter Decomposition☆23Updated this week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- ☆43Updated 6 months ago
- ☆10Updated 10 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆180Updated last week
- ☆31Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆247Updated last year
- ☆62Updated last week
- Tools for studying developmental interpretability in neural networks.☆90Updated 4 months ago
- ☆121Updated last year
- Sparse Autoencoder Training Library☆50Updated last month
- ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…☆60Updated this week
- ☆302Updated 2 weeks ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆34Updated last year
- ☆50Updated 3 weeks ago
- Modified to support crosscoder training.☆17Updated last week
- ☆28Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆154Updated last year
- ☆75Updated 3 months ago