Sheikh Abdur Raheem Ali (sheikheddy)

sheikheddy

User data from Github https://github.com/sheikheddy

Location:Dubai, UAE

GitHub:@sheikheddy

Sheikh Abdur Raheem Ali's repositories

License:MITStargazers:0Issues:0Issues:0
Language:Jupyter NotebookStargazers:0Issues:0Issues:0

CAA

Steering Llama 2 with Contrastive Activation Addition

Language:Jupyter NotebookLicense:MITStargazers:0Issues:0Issues:0

base-models-refuse

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

Language:PythonStargazers:0Issues:0Issues:0

claude-code

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

License:NOASSERTIONStargazers:0Issues:0Issues:0

crosscoder-model-diff-replication

Open source replication of Anthropic's Crosscoders for Model Diffing

Stargazers:0Issues:0Issues:0

devinterp

Quantifying degeneracy in toy models

Language:PythonStargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:0Issues:0

dotfiles

my personal terminal configurations for alignment research engineering

Stargazers:0Issues:0Issues:0

fae

(jax, tpu) nf4 matmuls for flux + t5 + onnx vae. vision SAE training and maxacts

Language:PythonLicense:MITStargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0
Language:Jupyter NotebookLicense:MITStargazers:0Issues:0Issues:0

hoyolab-auto-daily

Easiest, full free, and no BS Hoyolab daily check-in using GitHub Actions. Supports Zenless Zone Zero, Honkai: Star Rail, Genshin Impact, Honkai Impact 3rd, and Tears of Themis.

License:MITStargazers:0Issues:0Issues:0

Language-Model-SAEs

For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.

Language:Jupyter NotebookStargazers:0Issues:0Issues:0

llm-viz

3D Visualization of an GPT-style LLM

Stargazers:0Issues:0Issues:0

marc

Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"

Language:PythonLicense:MITStargazers:0Issues:0Issues:0
Language:PythonLicense:MITStargazers:0Issues:0Issues:0

motion-canvas

Visualize Your Ideas With Code

Language:TypeScriptLicense:MITStargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0

sae

Sparse autoencoders

License:MITStargazers:0Issues:0Issues:0

sae-rm

Using SAE's to interpret Reward Models (RM)

Stargazers:0Issues:0Issues:0
Stargazers:0Issues:1Issues:0

SAE-TS

Improving Steering Vectors by Targeting Sparse Autoencoder Features

Language:PythonLicense:MITStargazers:0Issues:0Issues:0
Language:Jupyter NotebookLicense:MITStargazers:0Issues:0Issues:0

sapiens

High-resolution models for human tasks.

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

semantic-router

Superfast AI decision making and intelligent processing of multi-modal data.

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

sheikheddy.github.io

My personal website

Language:HTMLStargazers:0Issues:0Issues:0

slt

Tools for studying developmental interpretability in neural networks.

Language:PythonStargazers:0Issues:0Issues:0

SwitchTransformers

Implementation of Switch Transformers from the paper: "Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity"

License:MITStargazers:0Issues:0Issues:0

unit

Next Generation Visual Programming System

License:MITStargazers:0Issues:0Issues:0