INDEX

Explanations

phrases indicating visual representations or illustrations of data

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

ształ

-0.60

ograph

-0.53

iempo

-0.53

esehen

-0.52

ibilidad

-0.51

 Illust

-0.51

erweise

-0.50

Doh

-0.48

Imagem

-0.48

 Shutter

-0.48

POSITIVE LOGITS

+:+

0.72

 BorderRadius

0.71

ThroughAttribute

0.69

enderror

0.68

@"/

0.66

 lenker

0.66

PointerException

0.63

NewUrlParser

0.61

 MainAxisSize

0.61

AsUp

0.61

Activations Density 0.014%

phrases indicating visual representations or illustrations of data

No Known Activations