INDEX

Explanations

references to the term "antichrist"

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

 Surviv

-0.57

 Mirage

-0.55

é¾

-0.53

 Sahara

-0.52

 maize

-0.49

 Shed

-0.47

uga

-0.46

 mammoth

-0.45

hawk

-0.45

 Garg

-0.45

POSITIVE LOGITS

otle

0.86

ocrats

0.83

opher

0.75

ocrat

0.75

ocratic

0.72

orian

0.72

ophe

0.72

ically

0.66

enburg

0.65

ophon

0.63

Activations Density 8.204%

references to the term "antichrist"

No Comments

No Known Activations