I have done various research projects during my Computer Science Master's at ETH Zürich and Computer Science Bachelor's at University of Copenhagen. The topics have been computational biology, neuroscience, computer vision and natural lanugage processing.

Master's Thesis: Understanding Features in Superposition
in Transformer Language Models

Understanding the internal representations in large language models like ChatGPT is an active field of research and superposition has been proposed as a concept to make sense of the structure of the representational spaces. Supervised by Dr. Mor Geva Pipek, this thesis investigated the concept of superposition empirically in realistic Transformer language models using linear probing and causal interventions. Though further work is needed, the experimental results are evidence that superposition is indeed a phenomenon in realistic Transformer language models.

Master's Semester Project: Hidden Markov Models
in InferCNVpy

Copy Number Variations are a specific kind of mutation often found in cancer. Inferring such mutations from single cell RNA data has important use cases in research and possibly in treatment. This practical project implemented pre-existing methods for inference using Hidden Markov Models, making it easy to use in conjuction with the already existing Python package InferCNVpy

Sed nunc ligula

Nullam et orci eu lorem consequat tincidunt vivamus et sagittis magna sed nunc rhoncus condimentum sem. In efficitur ligula tate urna. Maecenas massa sed magna lacinia magna pellentesque lorem ipsum dolor. Nullam et orci eu lorem consequat tincidunt. Vivamus et sagittis tempus.