INDEX

Explanations

words and phrases indicating something emerging or being revealed

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

tuuri

-0.45

ley

-0.43

lapis

-0.43

rimônio

-0.42

LEY

-0.42

 maille

-0.42

Statistiche

-0.42

щадь

-0.42

ixels

-0.41

izaje

-0.41

POSITIVE LOGITS

ChildScrollView

0.96

 dikeluarkan

0.85

 sacó

0.83

 mengeluarkan

0.83

 reappear

0.80

 heraus

0.79

 emerges

0.78

pearance

0.78

ออกมา

0.77

 betweenstory

0.74

Activations Density 0.155%

words and phrases indicating something emerging or being revealed

No Comments

No Known Activations