INDEX

Explanations

geographic references and locations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bats

-0.55

weed

-0.52

tailed

-0.51

 Shiv

-0.50

tons

-0.50

 Voltage

-0.50

amount

-0.50

MpServer

-0.48

 meshes

-0.48

minecraft

-0.48

POSITIVE LOGITS

Ö¼

0.67

ivals

0.63

orp

0.63

cial

0.61

urus

0.60

ĨĴ

0.59

OPE

0.59

agog

0.58

Ã±a

0.58

Pacific

0.57

Activations Density 8.342%

geographic references and locations

No Comments

No Known Activations