INDEX

Explanations

research-related terms and findings related to food consumption, circadian rhythms, and medical conditions

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Franch

-0.79

 brim

-0.78

Company

-0.78

Riy

-0.76

soDeliveryDate

-0.72

 Armageddon

-0.72

 yours

-0.71

gallery

-0.71

 Garage

-0.71

wered

-0.70

POSITIVE LOGITS

 biomark

1.40

 susceptibility

1.35

 phenotype

1.33

 âĪ¼

1.29

 antidepressant

1.29

 clinically

1.28

 correlated

1.27

 endogenous

1.27

 neuronal

1.27

 metabolic

1.26

Activations Density 3.950%

research-related terms and findings related to food consumption, circadian rhythms, and medical conditions

No Comments

No Known Activations