apartresearch Goto Github PK

.github

ai-psychology-starter

Code templates to get started as an AI psychologist

ais-cost-effectiveness

Cost-effectiveness models, tools, and results for various AI safety field-building programs.

aisafetyideas

💡 The web app CI/CD for aisafetyideas.com

alignmentmarkets

📈 Bet on the progress of AI safety benchmarks

apart-evals

blackbox-psych

Conducting psychology experiments on black box language models

deepdecipher

🦠 DeepDecipher: An open source API to MLP neurons

empathetic-ai

🤖 A systematic review on how to create empathetic AI

gooseaiunityapi

Integration for the OpenAi Api in Unity

gpt-4-chat-ui

GPT-4 frontend with open source Next.js template.

icml2024mi

🌍 Website for NeurIPS2023MI

integer_addition

✱ Understanding the underlying learning dynamics of simple tasks in Transformer networks

interpretability-starter

🧠 Starter templates for doing interpretability research

interpreting-reward-models

✱ Interpreting implicit reward models learnt in RLHF using sparse autoencoders.

mechanisticinterpretability

A repository for awesome resources in mechanistic interpretability

n2g

Tools for exploring Transformer neuron behaviour, including input pruning and diversification.

neuron2graph

Tools for exploring Transformer neuron behaviour, including input pruning and diversification.

open

🌍 Repository to update our open data

othelloscope

Interpretability Hackathon 2.0 entry

paper-website

🌍 Website template for academic papers

pysvelte

A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations

readingwhatwecan

📚📚📚📚📚📚📚📚📚 Reading everything

safety-timelines

📈 Research into when alignment is solved

scale-llm-24

🌍 Website for the Scaling Laws workshop

scaling-laws-viz

📈 Animating how AI FLOPs have developed over time

scheduling-widget

📆 Showcases specific times in local time zones

seqcont_circuits

✱ Interpreting how similar sequence continuation tasks share internal representations ✱

specificityplus

👩‍💻 Code for the ACL paper "Detecting Edit Failures in LLMs: An Improved Specificity Benchmark"

task-standard

🚨 METR Task Standard fork for the Code Red Hackathon