nrimsky / InfluenceFunctionsLinks
Implementation of Influence Function approximations for differently sized ML models, using PyTorch
☆15Updated last year
Alternatives and similar repositories for InfluenceFunctions
Users that are interested in InfluenceFunctions are comparing it to the libraries listed below
Sorting:
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 5 months ago
- Simple and scalable tools for data-driven pretraining data selection.☆24Updated last month
- ☆27Updated 5 months ago
- ☆60Updated 3 years ago
- Official code repo for paper "Great Memory, Shallow Reasoning: Limits of kNN-LMs"☆23Updated 2 months ago
- ☆23Updated 9 months ago
- Code for "Tracing Knowledge in Language Models Back to the Training Data"☆38Updated 2 years ago
- ☆45Updated last year
- ☆20Updated last year
- ☆35Updated 2 years ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆49Updated 9 months ago
- ☆29Updated 2 years ago
- Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models☆46Updated last year
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆30Updated 5 months ago
- Landing page for MIB: A Mechanistic Interpretability Benchmark☆15Updated this week
- ☆14Updated last year
- This is the official implementation for our ACL 2024 paper: "Causal Estimation of Memorisation Profiles".☆23Updated 3 months ago
- Sparse Autoencoder Training Library☆53Updated 2 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643☆76Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆37Updated 2 years ago
- ☆74Updated last year
- [ACL 2023]: Training Trajectories of Language Models Across Scales https://arxiv.org/pdf/2212.09803.pdf☆24Updated last year
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆27Updated last year
- In-context Example Selection with Influences☆15Updated 2 years ago
- ☆26Updated 2 years ago
- Data for "Datamodels: Predicting Predictions with Training Data"☆97Updated 2 years ago
- ☆54Updated 2 years ago