INDEX

Explanations

mentions of the word "message" or variations of it such as "messaging" or "Messenger" in a text

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

©¶æ

-0.91

DragonMagazine

-0.83

cember

-0.70

hyde

-0.70

steen

-0.67

LECT

-0.66

DEN

-0.66

ANK

-0.64

 pedals

-0.63

GGGGGGGG

-0.63

POSITIVE LOGITS

enger

1.17

aging

1.09

engers

1.05

ages

1.05

Mess

0.92

hof

0.88

inis

0.86

ipop

0.85

roth

0.83

 Mess

0.83

Activations Density 5.984%

mentions of the word "message" or variations of it such as "messaging" or "Messenger" in a text

No Comments

No Known Activations