INDEX

Explanations

references to philosophical and metaphysical concepts, alongside excerpts containing complex and intellectual discussions

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

 Cookie

-0.81

Klu

-0.68

 behavi

-0.68

 positives

-0.67

 stunts

-0.66

ebin

-0.66

ADS

-0.66

Kiw

-0.66

ãĥ¯ãĥ³

-0.66

 banana

-0.65

POSITIVE LOGITS

âĢ¢âĢ¢

1.02

Â§

0.97

Pg

0.91

á¸

0.87

Footnote

0.85

âĢł

0.84

—"

0.81

slave

0.80

âĢĳ

0.79

Activations Density 5.643%

references to philosophical and metaphysical concepts, alongside excerpts containing complex and intellectual discussions

No Comments

No Known Activations