INDEX

Explanations

phrases related to technical concepts and regulations

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

 helicop

-0.72

avorite

-0.70

 corrid

-0.69

 Rasmussen

-0.67

GGGGGGGG

-0.67

 Pengu

-0.62

 tatt

-0.62

 Splash

-0.62

ãĥĩãĤ£

-0.61

 nood

-0.61

POSITIVE LOGITS

 regards

0.88

ardless

0.79

equality

0.73

range

0.71

eous

0.69

orthern

0.69

unia

0.68

 regard

0.66

etics

0.66

arth

0.66

Activations Density 4.482%

phrases related to technical concepts and regulations

No Comments

No Known Activations