INDEX

Explanations

specific names of places, characters, or entities related to various contexts in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ویکی‌پدی

-0.47

 kaarangay

-0.43

Personendaten

-0.42

 linkovi

-0.40

ONOM

-0.39

хьтан

-0.37

 мәкал

-0.37

ByVersion

-0.37

ografija

-0.36

Jîn

-0.36

POSITIVE LOGITS

########.

0.73

transQ

0.62

 OFDb

0.50

 HasFactory

0.48

infant

0.47

enfone

0.46

ismet

0.45

 postIndex

0.45

sendStatus

0.44

toyota

0.44

Activations Density 0.731%

specific names of places, characters, or entities related to various contexts in the document

No Comments

No Known Activations