INDEX

Explanations

content related to death and suicide

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 ThemeData

-0.65

defineProperty

-0.52

 للمعارف

-0.49

ностях

-0.48

uncios

-0.48

मित

-0.47

лами

-0.47

 Cumber

-0.46

proken

-0.46

咤

-0.45

POSITIVE LOGITS

 death

0.92

death

0.81

uxxxx

0.77

 deaths

0.76

 euth

0.73

 Death

0.69

Death

0.66

DEATH

0.66

 demise

0.66

 DEATH

0.66

Activations Density 0.363%

content related to death and suicide

No Comments

No Known Activations