INDEX

Explanations

key phrases indicating gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 compromis

-0.51

IndentedString

-0.50

anmoins

-0.50

↵↵

-0.45

atrième

-0.45

★★★★☆

-0.45

тьяна

-0.45

DoubleQuotes

-0.44

Diweddarwch

-0.43

ViewFeatures

-0.43

POSITIVE LOGITS

EqualsAnd

0.73

 SwiftUI

0.73

nonatomic

0.69

WaitGroup

0.68

SuppressMessage

0.68

يميديا

0.66

ConstraintMaker

0.65

 Exactos

0.65

MemoryWarning

0.65

WithIdentifier

0.63

Activations Density 1.234%

key phrases indicating gratitude and appreciation

No Comments

No Known Activations