INDEX

Explanations

terms related to life events, mortality, and associated statistics

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

preceding "death", "died", or "dying"

np_acts-logits-general · gemini-2.0-flash

death and dying after personal pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

лоси

-0.47

 Bajos

-0.46

ghorn

-0.46

&=&\

-0.43

 hasattr

-0.43

 Silvio

-0.41

onCancel

-0.41

agu

-0.41

てもら

-0.41

simi

-0.41

POSITIVE LOGITS

 death

2.71

 died

2.54

death

2.35

 deaths

2.21

 Death

2.16

Death

2.13

 DEATH

2.10

 dying

2.00

DEATH

1.92

 Died

1.87

Activations Density 0.911%

terms related to life events, mortality, and associated statistics

preceding "death", "died", or "dying"

death and dying after personal pronouns

No Comments

No Known Activations