INDEX

Explanations

sentences related to visual or conceptual representations, whether in art, programming, society, or other contexts

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

iery

-0.86

cake

-0.81

sis

-0.79

nen

-0.78

stead

-0.72

kefeller

-0.71

launch

-0.69

idem

-0.69

nuts

-0.68

iless

-0.68

POSITIVE LOGITS

 representations

1.03

 representation

1.01

eering

0.99

 portray

0.98

 portrayal

0.95

DonaldTrump

0.92

 Represent

0.89

eers

0.87

ãĤ¼ãĤ¦ãĤ¹

0.84

 depiction

0.83

Activations Density 7.216%

sentences related to visual or conceptual representations, whether in art, programming, society, or other contexts

No Comments

No Known Activations