INDEX

Explanations

specific occurrences, details, or instances within a larger context

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

ORTS

-0.79

chens

-0.70

 Cheong

-0.69

bridge

-0.69

ULTS

-0.69

glass

-0.67

BIL

-0.67

/>

-0.65

pless

-0.65

frog

-0.64

POSITIVE LOGITS

ities

1.22

ity

0.94

ties

0.89

ised

0.86

 embodiments

0.82

itarian

0.81

istics

0.80

iott

0.78

anooga

0.78

izations

0.76

Activations Density 7.914%

specific occurrences, details, or instances within a larger context

No Comments

No Known Activations