INDEX

Explanations

references to notable individuals and their roles or characteristics

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

clothing (especially wear/wore)

np_acts-logits-general · gemini-2.0-flash

wearing clothes

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

 تضيفلها

-0.95

 disambiguazione

-0.82

IsContent

-0.63

ContentAsync

-0.63

ProgressHUD

-0.60

Xna

-0.60

UnusedPrivate

-0.59

GraphicsUnit

-0.57

 متعلقه

-0.56

forChild

-0.56

POSITIVE LOGITS

 wear

2.30

 wears

2.21

 wore

2.15

 wearing

2.05

 Wear

1.97

Wear

1.85

 worn

1.80

 WEAR

1.77

 Wearing

1.74

wear

1.74

Activations Density 0.179%

references to notable individuals and their roles or characteristics

clothing (especially wear/wore)

wearing clothes

No Comments

No Known Activations