INDEX

Explanations

expressions related to death or dying

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

death or dying

np_acts-logits-general · gemini-2.0-flash

death and dying

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 للاسماء

-0.80

ViewFeatures

-0.70

esez

-0.70

-0.65

soort

-0.65

tvguidetime

-0.64

marginHorizontal

-0.64

httphttps

-0.63

ChildScrollView

-0.62

 Fant

-0.61

POSITIVE LOGITS

die

0.96

Die

0.93

DIE

0.89

Die

0.88

 dies

0.75

die

0.71

 mourir

0.68

 died

0.66

 DIES

0.65

DIE

0.63

Activations Density 0.095%

expressions related to death or dying

death or dying

death and dying

No Comments

No Known Activations