tianyu139 / meaning-as-trajectories
Official PyTorch Implementation for Meaning Representations from Trajectories in Autoregressive Models (ICLR 2024)
☆10Updated 4 months ago
Related projects: ⓘ
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆18Updated last year
- ☆34Updated last year
- ☆27Updated last year
- Code for the paper "Data Feedback Loops: Model-driven Amplification of Dataset Biases"☆15Updated 2 years ago
- ☆12Updated 9 months ago
- Repo for: When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment☆37Updated last year
- Google Research☆45Updated last year
- Towards Understanding the Mixture-of-Experts Layer in Deep Learning☆19Updated 9 months ago
- We introduce EMMET and unify model editing with popular algorithms ROME and MEMIT.☆11Updated 3 weeks ago
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆34Updated last year
- ☆17Updated last year
- Minimum Description Length probing for neural network representations☆15Updated 11 months ago
- ☆23Updated last year
- Official code for the paper: "Metadata Archaeology"☆18Updated last year
- Tree prompting: easy-to-use scikit-learn interface for improved prompting.☆27Updated 10 months ago
- ☆15Updated 2 months ago
- Universal Neurons in GPT2 Language Models☆25Updated 3 months ago
- Code repository for the paper "Meta-Learning via Classifier(-free) Diffusion Guidance"☆30Updated last year
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Updated last year
- Official code repo for paper "Great Memory, Shallow Reasoning: Limits of kNN-LMs"☆15Updated 3 weeks ago
- Experiments on GPT-3's ability to fit numerical models in-context.☆14Updated 2 years ago
- ☆15Updated this week
- ☆12Updated 4 months ago
- ModelDiff: A Framework for Comparing Learning Algorithms☆52Updated last year
- ☆26Updated last year
- Official implementation of FIND (NeurIPS '23) Function Interpretation Benchmark and Automated Interpretability Agents☆42Updated 5 months ago
- ☆47Updated 3 months ago
- Sparse and discrete interpretability tool for neural networks☆51Updated 7 months ago
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆17Updated 5 months ago
- Code for "Merging Text Transformers from Different Initializations"☆18Updated last month