INDEX

Explanations

references to figures and graphical elements in a document

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MigrationBuilder

-0.63

ReusableCell

-0.62

))->

-0.59

didSet

-0.56

Portale

-0.55

-0.54

)}</

-0.54

 }}</

-0.53

}}</

-0.53

ゲー

-0.52

POSITIVE LOGITS

 Normdatei

0.80

 purpoſe

0.60

 Houſe

0.59

 Majefty

0.58

хьтан

0.57

 Chriftian

0.57

DateTimeField

0.56

Diweddarwch

0.56

 noDo

0.56

 Diſ

0.55

Activations Density 0.101%

references to figures and graphical elements in a document

No Comments

No Known Activations