Skip to main content

Indie game storeFree gamesFun gamesHorror games
Game developmentAssetsComics
SalesBundles
Jobs
TagsGame Engines
cmathw updated a tool 1 year ago
A downloadable tool.
1 new upload:
Hackathon Report_Chris_Guillaume.pdf 1.1 MB
Al-Hitawi Mohammed published a BlueTeam 1 year ago
A downloadable BlueTeam.
In order to achieve the desired behavior of an agent that learns from its mistakes and improves its performance, we need to get more familiar with the concept of Reinforcement Learning (RL). Implementing such a self-learning system is easie...
mentaleap published a project 1 year ago
clementneo published a project 1 year ago
A downloadable project.
How would a transformer know when to use ‘an’ rather than ‘a’? The autoregressive nature of the transformer means that it is only capable of predicting one token at a time, yet the choice between the words depends on the subsequent...
roksanagow published a research 1 year ago
A downloadable research.
As layers are chained together in a pipeline where each layer has knowledge on how to decode the information passed to it from the previous layer and how to process it to gain value that ultimately leads to a prediction. Thus, we hypothesis...
Giles published a project 1 year ago
A downloadable project.
https://github.com/edkins/universality
jakub151 published a project 1 year ago
A downloadable project.
In this research project we found tasks that a small language model had varied behavior on. Once we found interesting behavior we used the tools of mechanistic interpretability to dig deeper into why the model had varied behavior. We then s...
chris-lons published a project 1 year ago
A downloadable project.
We expand Neel Nanda's Interactive Neuroscope to view an entire layer. Looking at Neel Nanda's Interactive Neuroscope, we were stymied by the question of which neuron we ought to try to look at. It seemed potentially useful to be able to qu...
roksanagow published a research 1 year ago
A downloadable research.
Vision Transformers, just like other neural networks for image classification, have long been interpretable thanks to guided backpropagation to visualise attention. Likewise, simply by visualising them, it is clear that individual neurons i...
Esben Kran published a project 1 year ago
A downloadable project.
TraCR-Supported Mechanistic Interpretability We compare a Transformer compiled from a RASP algorithm using TRACR to a Transformer trained on the same task with AdamW using the TransformerLens library. We find that (1) compiled Transformers...
cmathw published a tool 1 year ago
A downloadable tool.
We identify the broad structure of a circuit that is associated with correctly predicting a gendered pronoun given the subject of a rhetorical question. Progress towards identifying this circuit is achieved through a variety of existing too...
Yoann Poupart published a tool 1 year ago
A downloadable tool.
Experiment on Iterative Summarisation, potentially linked to Natural Abstraction. Made for the Alignment jam #4. See the GitHub for more info.
MatthewBaggins published a project 1 year ago
A downloadable project.
We trained a single layer attention-only transformer to sort a fixed-length list of non-repeating tokens. It turned out to implement an operation consisting of looking into the unsorted list and searching for tokens that are greater than th...
Loading more…