INDEX

Explanations

news headlines and articles related to various events and topics

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

soType

-0.66

laughs

-0.59

font

-0.56

ãĤ´ãĥ³

-0.55

common

-0.53

é¾įå¥ĳå£«

-0.53

aturday

-0.52

actionDate

-0.52

fitting

-0.52

;;;;

-0.52

POSITIVE LOGITS

 disappeared

0.77

 magically

0.77

 survived

0.75

 went

0.73

 stayed

0.73

 mysteriously

0.73

 cannot

0.71

 vanished

0.71

 transitioned

0.70

 erased

0.70

Activations Density 20.234%

news headlines and articles related to various events and topics

No Comments

No Known Activations