tianyu139 / meaning-as-trajectoriesLinks
Official PyTorch Implementation for Meaning Representations from Trajectories in Autoregressive Models (ICLR 2024)
☆21Updated last year
Alternatives and similar repositories for meaning-as-trajectories
Users that are interested in meaning-as-trajectories are comparing it to the libraries listed below
Sorting:
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆124Updated 2 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Updated last year
- Sparse and discrete interpretability tool for neural networks☆63Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 9 months ago
- ☆106Updated 6 months ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆39Updated 9 months ago
- ☆19Updated 2 months ago
- ☆50Updated last year
- Code to enable layer-level steering in LLMs using sparse auto encoders☆25Updated 3 months ago
- ☆15Updated last year
- ☆43Updated 2 years ago
- ☆12Updated 2 years ago
- ☆28Updated 6 months ago
- PyTorch library for Active Fine-Tuning☆89Updated 6 months ago
- Repo for: When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment☆38Updated 2 years 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
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆90Updated 9 months ago
- The repository contains code for Adaptive Data Optimization☆25Updated 8 months ago
- Universal Neurons in GPT2 Language Models☆30Updated last year
- ☆72Updated last year
- Data for "Datamodels: Predicting Predictions with Training Data"☆97Updated 2 years ago
- NeurIPS'24 - LLM Safety Landscape☆28Updated 6 months ago
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆22Updated last year
- ☆17Updated last year
- ☆31Updated 2 years ago
- ☆23Updated 7 months ago
- ☆34Updated 7 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 10 months ago
- ☆51Updated 5 months ago
- Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]☆43Updated last year