INDEX

Explanations

punctuation marks and possessive forms indicating ownership or relationships

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

possessives and contractions

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

<bos>

-0.43

 الع

-0.43

 frie

-0.42

">//

-0.38

DP

-0.38

clo

-0.37

 instrumental

-0.36

 Stron

-0.36

 Vesta

-0.35

dra

-0.35

POSITIVE LOGITS

1.09

 ainfi

0.81

 feroit

0.77

 dezelve

0.72

 enfans

0.71

 étoient

0.68

 avoient

0.67

 Beſ

0.66

 Wikiseite

0.65

 Einfluß

0.62

Activations Density 0.193%

punctuation marks and possessive forms indicating ownership or relationships

possessives and contractions

No Comments

No Known Activations