INDEX

Explanations

terms related to death and homicide

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

death, dying, or mortality

np_acts-logits-general · gemini-2.0-flash

death, mortality, fatality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Tikang

-0.76

parsedMessage

-0.72

 Paglinawan

-0.72

NameInMap

-0.70

 FetchType

-0.69

unzel

-0.67

 パンチラ

-0.66

 CreateTagHelper

-0.66

 Numerade

-0.65

SequentialGroup

-0.65

POSITIVE LOGITS

 death

0.86

 deaths

0.77

death

0.65

 muerte

0.64

 död

0.63

 mortality

0.59

 DEATH

0.57

 muertes

0.57

 décès

0.56

 śmier

0.56

Activations Density 0.352%

terms related to death and homicide

death, dying, or mortality

death, mortality, fatality

No Comments

No Known Activations