INDEX

Explanations

information related to characters, plot descriptions, and settings in a story, likely related to books or movies

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

inventoryQuantity

-0.64

alam

-0.62

arth

-0.55

 alike

-0.52

thin

-0.52

 Conversely

-0.52

 extremes

-0.52

 stride

-0.51

quickShipAvailable

-0.49

 possessed

-0.49

POSITIVE LOGITS

yrinth

0.69

uggest

0.68

itled

0.64

named

0.60

 inviting

0.59

FY

0.59

FG

0.59

 Doodle

0.57

icial

0.56

matic

0.56

Activations Density 24.307%

information related to characters, plot descriptions, and settings in a story, likely related to books or movies

No Comments

No Known Activations