frankaging / Interchange-Intervention-TrainingLinks
The codebase for Inducing Causal Structure for Interpretable Neural Networks
☆10Updated 3 years ago
Alternatives and similar repositories for Interchange-Intervention-Training
Users that are interested in Interchange-Intervention-Training are comparing it to the libraries listed below
Sorting:
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆11Updated 4 months ago
- Align your LM to express calibrated verbal statements of confidence in its long-form generations.☆25Updated last year
- ☆36Updated 2 years ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆47Updated 8 months ago
- ☆9Updated last year
- CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior☆12Updated 2 years ago
- ☆50Updated last year
- Code for preprint: Summarizing Differences between Text Distributions with Natural Language☆42Updated 2 years ago
- Landing page for MIB: A Mechanistic Interpretability Benchmark☆10Updated last week
- "Understanding Dataset Difficulty with V-Usable Information" (ICML 2022, outstanding paper)☆86Updated last year
- ☆29Updated last year
- Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments (Zhou et al., EMNLP 2024)☆13Updated 8 months ago
- A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643☆76Updated last year
- This is the official implementation for our ACL 2024 paper: "Causal Estimation of Memorisation Profiles".☆21Updated 2 months ago
- Sparse probing paper full code.☆56Updated last year
- code for EMNLP 2024 paper: How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for M…☆11Updated 6 months ago
- code and data associated with CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations☆10Updated last year
- ☆30Updated 10 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆58Updated 6 months ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆41Updated 3 months ago
- Code for the paper "REV: Information-Theoretic Evaluation of Free-Text Rationales"☆15Updated last year
- Code for paper "Search Methods for Sufficient, Socially-Aligned Feature Importance Explanations with In-Distribution Counterfactuals"☆18Updated 2 years ago
- Augmenting Statistical Models with Natural Language Parameters☆26Updated 8 months ago
- ☆44Updated last year
- ☆34Updated 3 years ago
- ☆18Updated last year
- How do transformer LMs encode relations?☆48Updated last year
- [ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models☆61Updated 2 years ago
- ☆9Updated last year
- ☆44Updated last year