INDEX

Explanations

phrases that denote standard practices or commonly accepted beliefs

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

"The" followed by a superlative adjective

np_acts-logits-general · gemini-2.0-flash

the ultimate quality or rank

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

Personensuche

-0.88

rungsseite

-0.85

NameInMap

-0.83

 Monfieur

-0.83

tvguidetime

-0.82

Билгалдахарш

-0.80

 незавершена

-0.79

 initComponents

-0.78

TestingModule

-0.77

 Inſ

-0.76

POSITIVE LOGITS

 king

0.82

 epitome

0.77

 queen

0.68

 ultimate

0.67

 kings

0.66

 pinnacle

0.65

 quintessential

0.62

 KING

0.60

 King

0.59

 premier

0.55

Activations Density 0.167%

phrases that denote standard practices or commonly accepted beliefs

"The" followed by a superlative adjective

the ultimate quality or rank

No Comments

No Known Activations