Search Results for author:
Found 18 papers, 10 papers with code
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
TensorFlow is an interface for expressing machine learning algorithms, and an implementation for executing such algorithms.
Concrete Problems in AI Safety
Rapid progress in machine learning and artificial intelligence (AI) has brought increasing attention to the potential impacts of AI technologies on society.
The Building Blocks of Interpretability
In this article, we treat existing interpretability methods as fundamental and composable building blocks for rich user interfaces.
Differentiable Image Parameterizations
Typically, we parameterize the input image as the RGB values of each pixel, but that isn’t the only way.
Activation Atlas
By using feature inversion to visualize millions of activations from an image classification network, we create an explorable activation atlas of features the network has learned which can reveal how the network typically represents some concepts.
Feature Visualization
There is a growing sense that neural networks need to be interpretable to humans.
Thread: Circuits
To facilitate exploration of this direction, Distill is inviting a “thread” of short articles on circuits, interspersed with critical commentary by experts in adjacent fields.
High-Low Frequency Detectors
Yet, when systematically characterizing the early layers of InceptionV1, we found a full fifteen neurons of mixed3a that appear to detect a high frequency pattern on one side, and a low frequency pattern on the other.
Visualizing Weights
Trying to understand artificial neural networks also has a lot in common with neuroscience, which tries to understand biological neural networks.
Multimodal Neurons in Artificial Neural Networks
It’s the fact that you plug visual information into the rich tapestry of memory that brings it to life."
A General Language Assistant as a Laboratory for Alignment
We find that the benefits from modest interventions increase with model size, generalize to a variety of alignment evaluations, and do not compromise the performance of large models.
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
We apply preference modeling and reinforcement learning from human feedback (RLHF) to finetune language models to act as helpful and harmless assistants.
Scaling Laws and Interpretability of Learning from Repeated Data
To do this, we train a family of models where most of the data is unique but a small fraction of it is repeated many times.
Language Models (Mostly) Know What They Know
We study whether language models can evaluate the validity of their own claims and predict which questions they will be able to answer correctly.
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
We provide our own analysis of the data and find a variety of harmful outputs, which range from offensive language to more subtly harmful non-violent unethical outputs.
In-context Learning and Induction Heads
In this work, we present preliminary and indirect evidence for a hypothesis that induction heads might constitute the mechanism for the majority of all "in-context learning" in large transformer models (i. e. decreasing loss at increasing token indices).
