INDEX

Explanations

words related to death and homicide

oai_token-act-pair · gemini-2.0-flash

kill

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Hozzáférés

-0.59

RuleContext

-0.56

 Conti

-0.53

 Baillargeon

-0.53

lexia

-0.50

meal

-0.50

gink

-0.50

thold

-0.49

Personendaten

-0.49

ipedi

-0.48

POSITIVE LOGITS

 death

1.43

 died

1.33

 deaths

1.30

 dying

1.25

 Death

1.23

 dead

1.20

Death

1.20

death

1.19

 DEATH

1.15

 muerte

1.12

Activations Density 0.445%

words related to death and homicide

kill

No Comments

No Known Activations