My Projects

A showcase of my work in AI research, interpretability, and machine learning applications

Bible Project Preview Available on PyPI

Bible

Python NLP CLI PyPI

Scripture agentic application for Bible study and research. 

pip install biblia
Updated: 2025 v0.6.0
View Code PyPI
Greater Than Circuit Analysis Research

Greater Than Circuit

Python Mechanistic Interpretability TransformerLens GPT-2 AI Safety Research

Reverse-engineering the circuit responsible for numerical comparisons in GPT-2 Small using activation patching and mechanistic interpretability techniques.

Updated: 2025 AI Research
View Code Research
FinGPT Trader Preview Active

FinGPT Trader

Python LLM Finance ML

An algorithmic trading system based on FinGPT, demonstrating new applications of large pre-trained Language Models in quantitative finance.

Updated: 2025
Live Demo View Code
Sparse Autoencoder Research Preview Research

Exploring SAEs

Python PyTorch ML Interpretability AI Safety

Implementation and analysis of Sparse Autoencoders for neural network interpretability research. Features interactive visualization dashboard and W&B integration.

Updated: 2025
W&B Dashboard View Code
Weather Forecasting with LoRA Fine-tuning Active Research

Weather Forecasting with LoRA

Python LoRA Mistral-7B PPO RLHF HuggingFace

A comprehensive research implementation of weather forecasting using LoRA fine-tuning on Large Language Models, following Schulman et al. (2025) "LoRA Without Regret" methodology. Transforms numerical weather data into natural language forecasts through parameter-efficient fine-tuning with RLHF optimization.

Updated: 2025
Quick Start View Code
Web Research Agent Available on PyPI

Web Research Agent

Python LM Gemini API Agents PyPI

An autonomous research agent that performs web research, code analysis, and task automation using Gemini for reasoning and various APIs for interactions. 

pip install web-research-agent
Updated: 2025 v1.1.6
View Code PyPI
Chain-of-Thought Faithfulness Analysis Research

CoT Faithfulness Analysis

Python PyTorch TransformerLens Interpretability AI Safety MATS

Comprehensive mechanistic analysis of chain-of-thought faithfulness in GPT-2. Implements attribution graphs, faithfulness detection, and targeted interventions for understanding reasoning circuits in language models.

Updated: 2025 Independent
View Code Results
Value-Aligned Confabulation Research Research

Value-Aligned Confabulation (VAC)

Python AI Safety LLM Evaluation Value Alignment Research

Research framework for evaluating value-aligned confabulation in LLMs - distinguishing beneficial speculation from harmful hallucination. Implements novel metrics for the truthfulness-utility trade-off.

Updated: 2025 AI Safety Research
View Code Research Article