ckkissane

attention-output-saes

Code to reproduce key results for "Interpreting Attention Layer Outputs with Sparse Autoencoders"

base-models-refuse

Code to reproduce key results accompanying "Base LLMs refuse too"

crosscoder-model-diff-replication

Open source replication of Anthropic's Crosscoders for Model Diffing

deep_learning_curriculum

Language model alignment-focused deep learning curriculum

rlhf-shakespeare

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

sae-dataset-dependence

sae-transfer

Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"

sae_vis

Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).

shakespeare-transformer

Decoder only transformer trained on the works of Shakespeare

TransformerLens

ckkissane/crosscoder-model-diff-replication

Open source replication of Anthropic's Crosscoders for Model Diffing

ckkissane/rlhf-shakespeare

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

ckkissane/sae-transfer

Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"

ckkissane/sae-dataset-dependence

ckkissane/attention-output-saes

Code to reproduce key results for "Interpreting Attention Layer Outputs with Sparse Autoencoders"

ckkissane/deep_learning_curriculum

Language model alignment-focused deep learning curriculum

ckkissane/base-models-refuse

Code to reproduce key results accompanying "Base LLMs refuse too"

ckkissane/shakespeare-transformer

Decoder only transformer trained on the works of Shakespeare

ckkissane/sae_vis

Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).

ckkissane/optimizers-from-scratch

Implementations of popular optimizers in Pytorch

ckkissane/1L-Sparse-Autoencoder

ckkissane/ARENA_2.0

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

ckkissane/TransformerLens

ckkissane/attention-head-wiki

ckkissane/attn-sae-gelu-2l-viz

ckkissane/attn-sae-gpt2-small-viz

ckkissane/august-monthly-challenge

ckkissane/CircuitsVis

Mechanistic Interpretability Visualizations using React

ckkissane/induction-heads-transformer-lens

Replication of induction heads phase change results using TransformerLens and PyTorch

ckkissane/jax

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

ckkissane/mech-interp-practice

Collection of mechanistic interpretability practice problems with accompanying tutorials

ckkissane/micrograd-tensor

Extension of micrograd. Uses Tensors instead of Values

ckkissane/minitorch

The full minitorch student suite.

ckkissane/Neuroscope

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

ckkissane/othello_world

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

ckkissane/pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

ckkissane/sae_visualizer

ckkissane/SAELens

Training Sparse Autoencoders on Language Models

ckkissane/sparse_autoencoder

Sparse Autoencoder for Mechanistic Interpretability

ckkissane/sparse_coding

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