INDEX

Explanations

references to completeness or totality in various contexts

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

"whole" or "entire" preceding a noun

np_acts-logits-general · gemini-2.0-flash

whole or entire scope

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 nakalista

-0.80

 Brutus

-0.68

 الحره

-0.67

 sherds

-0.66

apunov

-0.66

 bacilli

-0.65

 pathologist

-0.63

 Liens

-0.61

 knots

-0.60

 Philist

-0.60

POSITIVE LOGITS

 entire

1.03

 thing

0.89

 whole

0.80

 ENTIRE

0.75

 Entire

0.73

entire

0.72

 entier

0.70

Entire

0.69

 gamut

0.68

 egész

0.68

Activations Density 0.087%

references to completeness or totality in various contexts

"whole" or "entire" preceding a noun

whole or entire scope

No Comments

No Known Activations