INDEX

Explanations

references to awards and recognitions in various contexts

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

Award or honor recipients

np_acts-logits-general · gemini-2.0-flash

awards and best player

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 esternos

-0.64

 المعيارى

-0.63

KommentareTeilen

-0.63

 disambiguazione

-0.62

Personensuche

-0.61

createCanvas

-0.61

WindowConstants

-0.60

 BoxDecoration

-0.56

Kjelder

-0.54

حوالہ

-0.54

POSITIVE LOGITS

 Best

1.11

Best

1.01

 best

0.92

best

0.87

 Most

0.82

 BEST

0.79

BEST

0.76

 meilleur

0.75

MVP

0.73

 miglior

0.73

Activations Density 0.128%

references to awards and recognitions in various contexts

Award or honor recipients

awards and best player

No Comments

No Known Activations