ckkissane Goto Github PK

1l-sparse-autoencoder

arena_2.0

Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.

attention-head-wiki

attn-sae-gelu-2l-viz

attn-sae-gpt2-small-viz

august-monthly-challenge

circuitsvis

Mechanistic Interpretability Visualizations using React

deep_learning_curriculum

Language model alignment-focused deep learning curriculum

induction-heads-transformer-lens

Replication of induction heads phase change results using TransformerLens and PyTorch

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

mech-interp-practice

Collection of mechanistic interpretability practice problems with accompanying tutorials

micrograd-tensor

Extension of micrograd. Uses Tensors instead of Values

minitorch

The full minitorch student suite.

neuroscope

Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons

numpy

The fundamental package for scientific computing with Python.

optimizers-from-scratch

Implementations of popular optimizers in Pytorch

othello_world

Emergent world representations: Exploring a sequence model trained on a synthetic task

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

rlhf-shakespeare

Shakespeare transformer fine-tuned to generate positive sentiment samples using RLHF

sae_visualizer

saelens

Training Sparse Autoencoders on Language Models

shakespeare-transformer

Decoder only transformer trained on the works of Shakespeare

sparse_autoencoder

Sparse Autoencoder for Mechanistic Interpretability

sparse_coding

Using sparse coding to find distributed representations used by neural networks.

transformerlens