INDEX

Explanations

punctuation marks used in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

UnusedPrivate

-0.42

バチ

-0.40

makeConstraints

-0.40

vaadin

-0.40

XtraBars

-0.39

IntoConstraints

-0.39

 كمان

-0.38

 mira

-0.37

 BitmapFactory

-0.37

έ

-0.36

POSITIVE LOGITS

BeginInit

0.65

Autoritní

0.62

الدراسه

0.56

 ujednoznacz

0.54

Hentet

0.54

 betrokken

0.50

principalTable

0.50

EndInit

0.49

 CommonModule

0.48

*)&

0.47

Activations Density 0.000%

punctuation marks used in text

No Comments

No Known Activations