Max Lamparth's starred repositories
PurpleLlama
Set of tools to assess and improve LLM security.
TransformerLens
A library for mechanistic interpretability of GPT-style language models
causalbackdoor
Code for backdoor paper
Fine-pruning-defense
Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (RAID 2018)
Differentiable-DAG-Sampling
Differentiable DAG Sampling (ICLR 2022)
ReinforcementLearning.jl
A reinforcement learning package for Julia
BeautifulAlgorithms.jl
Concise and beautiful algorithms written in Julia
SPHKernels.jl
Julia implementation of some common SPH kernels
texprlcount
Perl script that evaluates the word count of a tex document according to the PRL length guidelines