INDEX

Explanations

occurrences of formatting tokens or symbols in the text

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

inc

-0.51

 incomp

-0.49

CreateModel

-0.46

 linf

-0.45

Inc

-0.44

 startY

-0.43

出版年

-0.43

eadilan

-0.42

 bill

-0.42

bill

-0.42

POSITIVE LOGITS

OGND

0.95

Personensuche

0.89

 Paglinawan

0.86

 Signalez

0.78

setVerticalGroup

0.78

StructEnd

0.75

 cherchés

0.73

]';

0.72

 ویکی‌پدی

0.72

ChromeDriver

0.72

Activations Density 0.000%

occurrences of formatting tokens or symbols in the text

No Known Activations