Search Results for author:
Found 6 papers, 5 papers with code
BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards
Input-output safeguards are used to detect anomalies in the traces produced by Large Language Models (LLMs) systems.
Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models
We find that LMs internally decompose retrieval tasks in a modular way: middle layers at the last token position process the request, while late layers retrieve the correct entity from the context.
How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model
Concretely, we use mechanistic interpretability techniques to explain the (limited) mathematical abilities of GPT-2 small.
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
Research in mechanistic interpretability seeks to explain behaviors of machine learning models in terms of their internal components.
Towards self-organized control: Using neural cellular automata to robustly control a cart-pole agent
The observations of the environment are transmitted in input cells, while the values of output cells are used as a readout of the system.
A journey in ESN and LSTM visualisations on a language task
In this work, we trained ESNs and LSTMs on a Cross-Situationnal Learning (CSL) task.
