INDEX

Explanations

welcoming phrases and interactions

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

welcome to

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 autorytatywna

-0.59

 okuyayım

-0.48

-------

-0.48

期刊论文

-0.45

WebElementEntity

-0.43

出版年

-0.42

ulihan

-0.41

 Jeans

-0.41

 anguish

-0.41

 ApiException

-0.41

POSITIVE LOGITS

 welcome

0.68

welcome

0.65

Welcome

0.64

WELCOME

0.62

 welcomes

0.61

 welcoming

0.61

 Welcome

0.60

 WELCOME

0.59

 welcomed

0.56

 betweenstory

0.54

Activations Density 0.008%

welcoming phrases and interactions

welcome to

No Comments

No Known Activations