AI Safety

Explore AI Safety through related topics and the articles other pages reference most.

Explore articles

Reset filters
Browse subtopics: Interpretability

Articles that also belong to these categories. Counts cover all of AI Safety.

Showing 1-9 of 9 articles

Abliteration

Abliteration is the practice of removing refusal behavior from an open-weight large language model by editing its weights so that the model can no longer write a "refusal direction" into its residual stream.

InterpretabilityLarge Language Models

Mechanistic interpretability

Mechanistic interpretability (often abbreviated as mech interp or MI) is the field that reverse-engineers the internal computations of neural networks, particularly transformers

Interpretability

Nick Cammarata

Nick Cammarata is a machine learning researcher who works on mechanistic interpretability, the study of how the internal components of neural networks compute.

InterpretabilityPeople

Representation Engineering

Representation Engineering (often abbreviated RepE) is a top-down approach to artificial-intelligence transparency and control that reads and manipulates high-level concepts (such as honesty, harmlessness, and…

Interpretability