TristanThrush / perplexity-correlations
Simple and scalable tools for data-driven pretraining data selection.
☆18Updated last month
Alternatives and similar repositories for perplexity-correlations:
Users that are interested in perplexity-correlations are comparing it to the libraries listed below
- ☆38Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated 10 months ago
- 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 2 months ago
- ☆28Updated 8 months ago
- ☆18Updated 8 months ago
- ☆31Updated 2 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆71Updated 5 months ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆25Updated last year
- ☆66Updated 3 years ago
- ☆13Updated last year
- ☆46Updated last year
- ☆90Updated last month
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆22Updated last month
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆29Updated 2 months ago
- ☆61Updated last year
- ☆22Updated 6 months ago
- ☆22Updated last month
- ☆34Updated last year
- Implementation of PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆35Updated 4 months ago
- ☆23Updated last month
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆21Updated 11 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆62Updated this week
- ☆51Updated 10 months ago
- ☆37Updated last year
- Language models scale reliably with over-training and on downstream tasks☆96Updated last year
- A library for efficient patching and automatic circuit discovery.☆62Updated last month
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆60Updated 2 months ago
- ☆17Updated 3 weeks ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆99Updated last year
- ☆49Updated 7 months ago