INDEX

Explanations

research studies and scientific journal publications related to neuroscience and medical studies

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

 broom

-0.73

 caster

-0.70

 diseng

-0.67

gg

-0.65

custom

-0.64

 sheltered

-0.64

 Franch

-0.64

ostic

-0.63

 Cutter

-0.63

ggle

-0.63

POSITIVE LOGITS

Explore

1.07

 Proceedings

1.00

ournals

0.98

 published

0.97

 Neuroscience

0.95

published

0.92

dx

0.89

 neuroscience

0.88

 PLoS

0.85

 authors

0.85

Activations Density 0.174%

research studies and scientific journal publications related to neuroscience and medical studies

No Comments

No Known Activations