INDEX

Explanations

terms associated with consciousness and awareness

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

TagMode

-0.69

 Gret

-0.68

 Mulberry

-0.68

putra

-0.66

 Thebes

-0.66

 Sodom

-0.66

клопе

-0.66

 apothe

-0.66

mural

-0.66

upaten

-0.65

POSITIVE LOGITS

Conscious

1.38

 Conscious

1.36

 conscious

1.24

 consciousness

1.19

 Consciousness

1.13

conscious

1.12

consciousness

1.08

 consciously

0.88

 coscienza

0.77

 consci

0.75

Activations Density 0.003%

terms associated with consciousness and awareness

No Known Activations