Leveraging BERT and c-TF-IDF to create easily interpretable topics.

A library for mechanistic interpretability of GPT-style language models

Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens

Implementation of short answer scoring with various language models.

Steering Llama 2 with Contrastive Activation Addition

A fast inference library for running LLMs locally on modern consumer-class GPUs

Stop messing around with finicky sampling parameters and just use DRµGS!

Python package for ACT-R cognitive models

Generative Agents: Interactive Simulacra of Human Behavior

Transformer experiments

Inference code for LLaMA models

Deep Learning Docker Image

A Python module for use with Elsevier's APIs: Scopus, ScienceDirect, others.

datamining the parler datadump