INDEX

Explanations

medical terms and foreign words related to politics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 VIDE

-0.52

 carefully

-0.50

 hindsight

-0.49

\":

-0.48

DragonMagazine

-0.48

TextColor

-0.47

 advertisers

-0.46

 billboards

-0.46

 BALL

-0.45

 alerts

-0.45

POSITIVE LOGITS

ensis

1.05

pai

0.68

nih

0.67

gmail

0.67

orum

0.67

rique

0.66

Ã©e

0.64

uni

0.63

Ãł

0.63

Ãª

0.62

Activations Density 0.443%

medical terms and foreign words related to politics

No Comments

No Known Activations