INDEX

Explanations

phrases related to politics or controversies

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

 newsp

-0.67

typ

-0.60

soDeliveryDate

-0.60

gradient

-0.56

aret

-0.55

quickShipAvailable

-0.55

 Caller

-0.54

rade

-0.54

reports

-0.53

simple

-0.53

POSITIVE LOGITS

 emulate

0.93

 take

0.92

be

0.90

 prove

0.88

 keep

0.87

 reach

0.86

 participate

0.85

 fulfill

0.84

 grasp

0.83

 avoid

0.82

Activations Density 10.263%

phrases related to politics or controversies

No Comments

No Known Activations