msakarvadia / AttentionLens
Interpretating the latent space representations of attention head outputs for LLMs
☆30Updated 5 months ago
Alternatives and similar repositories for AttentionLens:
Users that are interested in AttentionLens are comparing it to the libraries listed below
- Open source replication of Anthropic's Crosscoders for Model Diffing☆28Updated 2 months ago
- ☆41Updated this week
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆18Updated 9 months ago
- ☆12Updated 10 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆67Updated 2 months ago
- Universal Neurons in GPT2 Language Models☆27Updated 7 months ago
- ☆44Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated 7 months ago
- ☆23Updated 2 months ago
- ☆43Updated 5 months ago
- ☆37Updated 9 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆35Updated 3 months ago
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated last year
- ☆21Updated 2 months ago
- A library for efficient patching and automatic circuit discovery.☆46Updated last month
- ☆26Updated last year
- [ACL 2024] Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning☆34Updated 5 months ago
- Official code repo for paper "Great Memory, Shallow Reasoning: Limits of kNN-LMs"☆21Updated 4 months ago
- ☆16Updated 6 months ago
- Self-Supervised Alignment with Mutual Information☆16Updated 7 months ago
- ☆17Updated last month
- Learning adapter weights from task descriptions☆15Updated last year
- Implementation of Influence Function approximations for differently sized ML models, using PyTorch☆15Updated last year
- ☆52Updated last year
- Sparse Autoencoder Training Library☆38Updated 2 months ago
- nanoGPT-like codebase for LLM training☆83Updated this week
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆64Updated 7 months ago
- ☆26Updated 6 months ago
- Lightweight Adapting for Black-Box Large Language Models☆19Updated 11 months ago
- Align your LM to express calibrated verbal statements of confidence in its long-form generations.☆20Updated 7 months ago