msakarvadia / AttentionLens
Interpretating the latent space representations of attention head outputs for LLMs
☆30Updated 6 months ago
Alternatives and similar repositories for AttentionLens:
Users that are interested in AttentionLens are comparing it to the libraries listed below
- A library for efficient patching and automatic circuit discovery.☆53Updated this week
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated 8 months ago
- ☆12Updated 11 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆39Updated 3 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆70Updated 3 months ago
- ☆53Updated last year
- ☆18Updated 2 months ago
- Sparse Autoencoder Training Library☆41Updated 3 months ago
- ☆26Updated last year
- ☆24Updated 3 months ago
- Universal Neurons in GPT2 Language Models☆27Updated 8 months ago
- Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models☆43Updated last year
- [ACL 2024] <Large Language Models for Automated Open-domain Scientific Hypotheses Discovery>. It has also received the best poster award …☆38Updated 3 months ago
- Simple and scalable tools for data-driven pretraining data selection.☆14Updated last week
- ☆52Updated 4 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated last month
- ☆18Updated 3 months ago
- ☆44Updated last year
- ☆24Updated this week
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆38Updated 4 months ago
- ☆31Updated last week
- ☆27Updated 3 months ago
- nanoGPT-like codebase for LLM training☆89Updated this week
- ☆27Updated 3 months ago
- Dataset and evaluation suite enabling LLM instruction-following for scientific literature understanding.☆32Updated 2 months ago
- ☆55Updated 3 months ago
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆89Updated 3 years ago
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment☆50Updated 8 months ago
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Updated last year