A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
-
Updated
Nov 29, 2024
A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
Module 5: Open Research Software and Open Source
DDoS attack detection using BLSTM based RNN
OLS website: web presence and knowledge management for we-are-ols.org
Big five trait scores for 307,313 people from many different countries.
Development of an open data training program for Mozilla Science Labs.
A hands-on book for abusing systems using Rust (WIP) - Open Research
Our discussion forum (see "issues") for the OpenCon Do-A-Thon, a day of trying, making, testing and doing to advance Open Research & Education. See our full website, with more information (including Github Help, and how to get involved).
Code respository for AutSPACEs: the Autistica/Turing citizen science platform
Collective Knowledge repository with actions to unify the access to different predictive analytics engines (scipy, R, DNN) from software, command line and web-services via CK JSON API:
Meta information about platforms participating in experiment crowdsourcing using Collective Knowledge Framework (OS,CPU,GPU,GPGPU,NN...):
Collective Knowledge extension to automate Docker "build","run" and "push" functions and packge CK repositories for collaborative and reproducible research:
an initiative to provide infrastructure for reproducible workflows around open data
Crowdsourcing video experiments (such as collaborative benchmarking and optimization of DNN algorithms) using Collective Knowledge Framework across diverse Android devices provided by volunteers. Results are continuously aggregated in the open repository:
Collective Knowledge packages to build development versions of compilers (LLVM, GCC, etc) and use them in customizable and portable CK research workflows:
Android application to participate in experiment crowdsourcing (such as workload crowd-benchmarking and crowd-tuning) using Collective Knowledge Framework and open repositories of knowledge:
Public data sets and their properties in the Collective Knowledge Format with JSON API and JSON meta information to be easily pluggable to customizable and reproducible CK experimental workflows (such as collaborative program analysis and optimization):
Materials related to events I might attend, and to talks I am giving
Shared artifacts in the Collective Knowledge Format as a proof-of-concept to reproduce our recent Collective Mind- and Collective Knowledge-related papers
Add a description, image, and links to the open-research topic page so that developers can more easily learn about it.
To associate your repository with the open-research topic, visit your repo's landing page and select "manage topics."