INDEX

Explanations

sentences with the word "remains" followed by a verb

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

inse

-0.78

thood

-0.68

ier

-0.63

ovo

-0.59

eger

-0.58

ilar

-0.58

ooters

-0.56

eus

-0.56

aired

-0.54

iman

-0.53

POSITIVE LOGITS

 haunted

0.69

 tremend

0.67

 unresolved

0.62

 unsolved

0.60

 mysteries

0.59

IONS

0.59

 Unsure

0.58

 resurg

0.58

 unanswered

0.58

 indebted

0.57

Activations Density 12.080%

sentences with the word "remains" followed by a verb

No Comments

No Known Activations