INDEX

Explanations

mentions of reading devices and their functionalities

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

 CURIAM

-0.50

 TextAppearance

-0.40

LabelTagHelper

-0.39

🔕

-0.39

 Taip

-0.38

 competing

-0.37

ScopeManager

-0.36

hésite

-0.36

 opposing

-0.35

 Профиль

-0.35

POSITIVE LOGITS

 AssemblyCulture

0.56

LookAnd

0.54

 Chwiliwch

0.49

ApiModelProperty

0.48

Datuak

0.46

IVEREF

0.46

Portale

0.46

 jsPsych

0.46

لينكات

0.45

XmlAccessType

0.45

Activations Density 0.475%

mentions of reading devices and their functionalities

No Comments

No Known Activations