INDEX

Explanations

references to "Bon" and variations of the term related to context or subject matter

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

"Bon" followed by another word

np_acts-logits-general · gemini-2.0-flash

words starting with bon

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

migrationBuilder

-0.56

XtraReports

-0.55

jár

-0.53

ństwa

-0.52

FontOfSize

-0.51

 IconData

-0.50

 виправивши

-0.49

ństwo

-0.49

 vulgaires

-0.49

glUniform

-0.47

POSITIVE LOGITS

Bon

0.81

Bon

0.81

bon

0.80

 Bons

0.78

BON

0.75

Bons

0.74

BON

0.70

MemoryWarning

0.68

bon

0.67

bons

0.66

Activations Density 0.089%

references to "Bon" and variations of the term related to context or subject matter

"Bon" followed by another word

words starting with bon

No Comments

No Known Activations