INDEX

Explanations

expressions of greeting and welcome messages

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

"Welcome" or welcoming phrases

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

BeginInit

-0.40

LabelTagHelper

-0.39

 ligiloj

-0.36

fromnode

-0.34

CompilerServices

-0.34

CompleteListener

-0.33

✭✭

-0.32

CharacterOffset

-0.32

uffe

-0.32

Попис

-0.32

POSITIVE LOGITS

welcome

0.70

 welcoming

0.70

 bienvenida

0.67

 welcomes

0.66

elcome

0.65

WELCOME

0.65

 Willkommen

0.65

Wel

0.65

Welcome

0.61

Wel

0.61

Activations Density 0.049%

expressions of greeting and welcome messages

"Welcome" or welcoming phrases

No Comments

No Known Activations