INDEX

Explanations

references to bomb-related incidents or attacks

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

crime or violence

np_acts-logits-general · gemini-2.0-flash

crimes and destruction

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 vaisseaux

-0.62

 Purcell

-0.61

 bicchiere

-0.61

Datuak

-0.59

ftagPool

-0.57

FetchType

-0.56

 parteci

-0.55

 sélectionnés

-0.55

 devenus

-0.54

glVertex

-0.53

POSITIVE LOGITS

 vandal

0.77

 vandalism

0.77

 anonymously

0.70

 vand

0.63

 myster

0.60

 prank

0.59

 graffiti

0.56

Rüyada

0.54

 Vandal

0.54

 mysterious

0.53

Activations Density 0.230%

references to bomb-related incidents or attacks

crime or violence

crimes and destruction

No Comments

No Known Activations