hannamw / EAP-IG
☆13Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for EAP-IG
- ☆102Updated last month
- ☆75Updated 9 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆26Updated 5 months ago
- A library for efficient patching and automatic circuit discovery.☆30Updated last month
- Algebraic value editing in pretrained language models☆57Updated last year
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆61Updated 10 months ago
- ☆105Updated this week
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆31Updated last month
- ☆70Updated 3 months ago
- ☆32Updated last year
- ☆43Updated 4 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆25Updated 5 months ago
- ☆187Updated last month
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆52Updated last week
- ☆68Updated 3 months ago
- Sparse Autoencoder Training Library☆26Updated 2 weeks ago
- Using sparse coding to find distributed representations used by neural networks.☆181Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆118Updated last month
- AI Logging for Interpretability and Explainability🔬☆88Updated 5 months ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆36Updated 3 months ago
- ☆35Updated 9 months ago
- How do transformer LMs encode relations?☆37Updated 8 months ago
- Steering Llama 2 with Contrastive Activation Addition☆95Updated 5 months ago
- ☆96Updated 3 months ago
- Sparse probing paper full code.☆50Updated 10 months ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆29Updated 8 months ago
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆85Updated 3 years ago
- Align your LM to express calibrated verbal statements of confidence in its long-form generations.☆19Updated 5 months ago
- ☆59Updated 2 years ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆52Updated last month