Skip to main content

Indie game storeFree gamesFun gamesHorror games
Game developmentAssetsComics
SalesBundles
Jobs
Tags

Results

15 entries were submitted between 2023-01-20 16:00:00 and 2023-01-23 03:15:00. 52 ratings were given to 15 entries (100.0%) between 2023-01-23 03:15:00 and 2023-01-25 14:00:00. The average number of ratings per game was 3.5 and the median was .

Identifying a Preliminary Circuit for Predicting Gendered Pronouns in GPT-2 Small

by cmathw

Ranked 1st in Mechanistic interpretability with 7 ratings (Score: 4.571)

View submission page

CriteriaRankScore*Raw Score
Mechanistic interpretability#14.5714.571
Judge's choice#2n/an/a
Generality#43.2863.286
ML Safety#43.4293.429
Reproducibility#44.1434.143
Novelty#83.0003.000

We Discovered An Neuron

by clementneo

Ranked 2nd in Mechanistic interpretability with 5 ratings (Score: 4.400)

View submission page

CriteriaRankScore*Raw Score
Judge's choice#1n/an/a
Reproducibility#14.4004.400
Mechanistic interpretability#24.4004.400
Novelty#34.2004.200
Generality#112.8002.800
ML Safety#112.8002.800

Interactive Layerscope

by chris-lons, victorlf4

Ranked 3rd in Mechanistic interpretability with 3 ratings (Score: 4.333)

View submission page

CriteriaRankScore*Raw Score
Generality#14.3334.333
Mechanistic interpretability#34.3334.333
Novelty#73.3333.333
ML Safety#83.0003.000
Reproducibility#93.6673.667
No image :(

One Attention Head Is All You Need for Sorting Fixed-Length Lists

by MatthewBaggins

Ranked 3rd in Mechanistic interpretability with 3 ratings (Score: 4.333)

View submission page

CriteriaRankScore*Raw Score
Mechanistic interpretability#34.3334.333
Reproducibility#54.0004.000
Novelty#63.6673.667
Generality#122.6672.667
ML Safety#132.6672.667

TraCR-Supported Mechanistic Interpretability

by Esben Kran, ElliotJDavies, h6

Ranked 5th in Mechanistic interpretability with 4 ratings (Score: 4.250)

View submission page

CriteriaRankScore*Raw Score
ML Safety#13.7503.750
Novelty#14.5004.500
Generality#53.0003.000
Mechanistic interpretability#54.2504.250
Reproducibility#54.0004.000

Automated Identification of Potential Feature Neurons

by lomichelle42

Ranked 5th in Mechanistic interpretability with 4 ratings (Score: 4.250)

View submission page

CriteriaRankScore*Raw Score
Judge's choice#3n/an/a
Reproducibility#34.2504.250
Mechanistic interpretability#54.2504.250
Generality#53.0003.000
Novelty#83.0003.000
ML Safety#122.7502.750

Attention Phrenology: A spatial classification of attention heads

by Giles, soy.cola

Ranked 7th in Mechanistic interpretability with 4 ratings (Score: 4.000)

View submission page

CriteriaRankScore*Raw Score
Novelty#14.5004.500
Generality#24.0004.000
ML Safety#33.5003.500
Mechanistic interpretability#74.0004.000
Reproducibility#103.5003.500

Trafo Mech Int on the web!

by StefanHex

Ranked 8th in Mechanistic interpretability with 5 ratings (Score: 3.800)

View submission page

CriteriaRankScore*Raw Score
Reproducibility#14.4004.400
Generality#33.4003.400
ML Safety#73.2003.200
Mechanistic interpretability#83.8003.800
Novelty#122.6002.600

Soft Prompts are a Convex Set

by mentaleap

Ranked 9th in Mechanistic interpretability with 4 ratings (Score: 3.750)

View submission page

CriteriaRankScore*Raw Score
Judge's choice#4n/an/a
Novelty#43.7503.750
Reproducibility#54.0004.000
Generality#53.0003.000
ML Safety#63.2503.250
Mechanistic interpretability#93.7503.750

The Start of Investigating a 1-Layer SoLU Model

by jakub151

Ranked 10th in Mechanistic interpretability with 2 ratings (Score: 3.674)

View submission page

CriteriaRankScore*Raw Score
Novelty#53.6744.500
Reproducibility#83.6744.500
Generality#92.8583.500
ML Safety#92.8583.500
Mechanistic interpretability#103.6744.500
No image :(

In search of linguistic concepts: investigating BERT's context vectors

by roksanagow

Ranked 11th in Mechanistic interpretability with 3 ratings (Score: 3.333)

View submission page

CriteriaRankScore*Raw Score
ML Safety#53.3333.333
Generality#53.0003.000
Novelty#112.6672.667
Mechanistic interpretability#113.3333.333
Reproducibility#142.0002.000
No image :(

Distillation by duplication: The importance of layer selection

by roksanagow

Ranked 12th in Mechanistic interpretability with 2 ratings (Score: 2.858)

View submission page

CriteriaRankScore*Raw Score
Generality#92.8583.500
Novelty#102.8583.500
Mechanistic interpretability#122.8583.500
ML Safety#141.6332.000
Reproducibility#151.6332.000

Iterative summarization interpretability

by Yoann Poupart

Ranked 13th in Mechanistic interpretability with 2 ratings (Score: 2.449)

View submission page

CriteriaRankScore*Raw Score
ML Safety#92.8583.500
Reproducibility#112.8583.500
Generality#132.4493.000
Mechanistic interpretability#132.4493.000
Novelty#132.4493.000
No image :(

$B$ Confident Bro: Discovering Latent Knowledge In Language Models Without Supervision

by fbarez

Ranked 14th in Mechanistic interpretability with 2 ratings (Score: 1.225)

View submission page

CriteriaRankScore*Raw Score
ML Safety#23.6744.500
Reproducibility#132.0412.500
Generality#141.6332.000
Mechanistic interpretability#141.2251.500
Novelty#142.0412.500
No image :(

Investigating Agent Behavior In different RL methods

by Al-Hitawi Mohammed

Ranked 15th in Mechanistic interpretability with 2 ratings (Score: 0.816)

View submission page

CriteriaRankScore*Raw Score
Reproducibility#122.4493.000
Generality#141.6332.000
ML Safety#141.6332.000
Mechanistic interpretability#150.8161.000
Novelty#150.8161.000