INDEX

Explanations

terms related to death and dying

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

geot

-0.63

CSP

-0.62

xane

-0.61

stron

-0.60

medes

-0.60

 pinulongan

-0.59

annia

-0.59

 Kite

-0.59

RequestContext

-0.59

DIB

-0.59

POSITIVE LOGITS

 death

0.91

 muerte

0.88

death

0.87

Death

0.83

 Death

0.80

 DEATH

0.75

 śmier

0.72

 morte

0.71

 Muerte

0.68

 mortality

0.66

Activations Density 0.288%

terms related to death and dying

No Comments

No Known Activations