Skip to content
← Back to theses and internships

Master's thesis

Master's Thesis: Mechanistic Interpretability with Singular Value Decompositions

Fraunhofer · Darmstadt, Germany

Posted · Deadline: Not specified — apply early

Posted by Admin · VerifiedVerified active· Checked 20 Nov 2026

Master's thesis at Fraunhofer: key facts

Opportunity type
Master's thesis
Organization
Fraunhofer
Location
Darmstadt, Germany
Field / discipline
Technology and Software, Data and Analytics
Application deadline
Deadline not specified — apply early
Last source check
20 Nov 2026

About this master's thesis at Fraunhofer

Background and Motivation

Activation functions are a fundamental part of machine learning, as they introduce a non-linear component and thus make it possible to approximate arbitrary functions. In practice, these functions can have several million dimensions per layer of a neural network, which lead to the model’s prediction layer by layer through linear combinations and subsequent activation. Algebraically and numerically, it is also possible to transform the matrices in such a way that the products remain the same, while the factors are chosen cleverly so that individual features can be emphasized more strongly.

Goal

The thesis will investigate how exactly methods of mechanistic interpretability relate to the vector spaces of the activations, and whether, for example, safety features can be strengthened or weakened through targeted transformation of the matrices.

Results

The thesis should show whether manual transformations of the parameters are possible in principle, and whether a careful choice of bases, for example through orthogonalization, yields linear combinations that allow individual capabilities to be influenced in a targeted way.

Be part of change

Research and implement novel machine learning approaches that improve the safety of LLMs

Critically evaluate your results

Present your results

Write a project report in the form of a master’s thesis

Before you apply

0 of 4 ready

A preparation checklist, saved in this browser on this device without an account. It does not sync across devices. The official posting determines eligibility and required documents.

CV, motivation letter, and supervisor email templates

How to apply

Apply via jobs.fraunhofer.de. Check the original listing for required documents and submission instructions.

Source and listing information

Application source: jobs.fraunhofer.de. Listing details may change; confirm them on the source site. A source check confirms page availability, not endorsement of the organization.

Report an outdated or incorrect listing

Explore similar theses and internships

More opportunities

Browse all theses and internships