INDEX

Explanations

terms associated with causes and consequences of death, specifically in relation to medical conditions and incidents

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

death and 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-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

USO

-0.35

interface

-0.34

magnitude

-0.34

 interface

-0.33

Gea

-0.32

glLoad

-0.32

maß

-0.32

 незавершена

-0.32

dú

-0.31

NSP

-0.31

POSITIVE LOGITS

 death

2.80

death

2.38

 deaths

2.33

 DEATH

2.19

Death

2.17

 Death

2.16

 muerte

2.08

 died

1.98

DEATH

1.97

 morte

1.84

Activations Density 0.627%

terms associated with causes and consequences of death, specifically in relation to medical conditions and incidents

death and dying

death and dying

No Comments

No Known Activations