About Me
I'm an independent researcher focused on AI safety, working to develop a mechanistic understanding of how large language models process and reason about information. My research covers machine unlearning, modularity, and understanding planning in transformers - all aimed at understanding how these systems work on a larger scale.
With a background in theoretical physics and competitive mathematics, I combine research with practical engineering. I've built everything from quantum spin simulations to full-stack web apps and mobile applications. These days I mostly write Python for ML research, but I'm comfortable working across the stack.
Main Projects
Extracting Paragraphs from LLM Token Activations
Investigated how language models encode and plan paragraph-level information by analyzing single-token activations. Developed methods to extract and transfer contextual information between different prompts using activation patching techniques. Demonstrated that models maintain strong contextual awareness during text generation.
View Project
Dissecting Language Models: Machine Unlearning via Selective Pruning
Introduced a novel machine unlearning method for LLMs that uses selective pruning to remove specific capabilities while retaining others. The method identifies and removes neurons based on their relative importance to targeted capabilities vs overall network performance. Demonstrated state-of-the-art results in selective capability removal while maintaining model performance on other tasks.
View Project
Modularity in Transformers: Investigating Neuron Separability & Specialization
Researched modularity and task specialization within transformer architectures, focusing on both vision and language models. Combined selective pruning and clustering techniques to analyze how different neurons specialize in various tasks. Found evidence of task-specific neuron clusters with varying degrees of overlap between related tasks.
View Project
Investigating Neuron Ablation in Attention Heads
Developed a novel 'peak ablation' method for analyzing attention mechanisms in transformer models. Compared different neuron ablation techniques and their effects on model performance. Research provided insights into how attention neurons represent information and how different ablation methods affect model behavior.
View Project
Machine Learning for Many-Spin Quantum Systems
Worked on finding the ground state of quantum spins in different lattice configurations using different algorithms, in particular, looking at how different neural network models may be a way of getting better results.
View Project
Meteor Website
Created an automated website for looking through a database of meteor images and allowing user input
View Project
Painless Journal App
Worked in a team to develop a Flutter App for tracking and managing chronic pain symptoms
View Project
Society Events Website
A website that scrapes and saves data from facebook to connect students to events in Trinity College.
View Project
SGX Twilio
Created a bridge from twilio phone numbers to XMPP to the specification of Soprani.ca that allows the use of twilio phone numbers for normal texting.
View Project
Ray Tracing Physics Project
Studied the physics of ray-tracing simulation in a team and built a C++ program to better study implementation.
View Project
Sorting Algorithm Visualizer
A tool for visualising common sorting algorithms: Merge, Quick, Heap & Bubble Sort.
View Project
Rigid Body Simulation
Created a 3D interactive rigid-body simulator using advanced integration techniques, such as Green's Theorem.
View Project