INDEX

Explanations

punctuation marks and their variations in usage

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 MainAxisSize

-0.56

yntaxException

-0.56

ernalia

-0.55

 Biôgrafia

-0.54

 utafitiHapana

-0.54

 arşivlendi

-0.53

 iNdEx

-0.52

thâu

-0.52

 typelib

-0.52

 estekak

-0.52

POSITIVE LOGITS

richTextPanel

0.47

########.

0.46

 okuyayım

0.45

 Lawrence

0.40

ckså

0.40

Lorem

0.38

 جدا

0.37

 susten

0.37

 LAWRENCE

0.37

Lawrence

0.36

Activations Density 0.660%

punctuation marks and their variations in usage

No Comments

No Known Activations