INDEX

Explanations

words related to media adaptations and replicas

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

 territ

-0.95

usters

-0.95

ieri

-0.89

orney

-0.89

mediate

-0.89

cellaneous

-0.86

imb

-0.85

aiman

-0.85

redo

-0.83

iencies

-0.83

POSITIVE LOGITS

 thereof

1.94

of

1.20

UID

1.07

 version

1.07

 versions

1.02

esan

0.93

Of

0.89

arium

0.87

 Reborn

0.87

rait

0.85

Activations Density 1.623%

words related to media adaptations and replicas

No Comments

No Known Activations