INDEX

Explanations

references to specific names or entities, particularly individuals and organizations

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

Appears before surnames

np_acts-logits-general · gemini-2.0-flash

surname parts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

currentColor

-0.53

gación

-0.51

 upper

-0.51

 Wallflower

-0.49

Upper

-0.49

 Upper

-0.48

mazon

-0.48

 обез

-0.48

роль

-0.47

Vidite

-0.47

POSITIVE LOGITS

 kasarigan

0.68

دانشنامهٔ

0.63

complexType

0.58

SharedCtor

0.56

yard

0.54

neman

0.54

zel

0.53

zer

0.50

ArrowToggle

0.50

YARD

0.50

Activations Density 0.255%

references to specific names or entities, particularly individuals and organizations

Appears before surnames

surname parts

No Comments

No Known Activations