INDEX

Explanations

terms related to academic or mathematical notation

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

LookAnd

-0.69

richTextPanel

-0.63

Hentet

-0.61

StoryboardSegue

-0.60

 ویکی‌پدی

-0.57

URIComponent

-0.54

})));

-0.54

InstrumentedTest

-0.54

Хьажоргаш

-0.53

providedIn

-0.52

POSITIVE LOGITS

enumi

0.68

 useHistory

0.55

 rootReducer

0.55

kening

0.55

 seaborn

0.54

 useRouter

0.53

 tslint

0.53

 useNavigate

0.52

ModelMap

0.52

TargetException

0.51

Activations Density 0.001%

terms related to academic or mathematical notation

No Known Activations