INDEX

Explanations

specific numbered or lettered items within lists or enumerated points

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

 }}$}

-0.62

 بيها

-0.59

."]

-0.56

Билгалдахарш

-0.55

lrrrr

-0.55

})`

-0.55

archiviato

-0.54

 useSelector

-0.53

 Dostupné

-0.52

]");

-0.52

POSITIVE LOGITS

ViewFeatures

0.57

PreExecute

0.57

IndentedString

0.57

 ytter

0.56

StructEnd

0.55

Personensuche

0.54

vscode

0.54

WebControls

0.54

 /\.(

0.52

 MotionEvent

0.51

Activations Density 0.017%

specific numbered or lettered items within lists or enumerated points

No Known Activations