INDEX

Explanations

numerical data related to television ratings

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

age demographic numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 benih

-0.43

 rescat

-0.43

 hamil

-0.41

 nocturna

-0.40

ffeine

-0.40

 Jungen

-0.39

 Dichtung

-0.39

 galinha

-0.38

Scénario

-0.38

 Stimmung

-0.38

POSITIVE LOGITS

tagHelperRunner

0.78

 Италијани

0.77

Tikang

0.74

 noDo

0.71

 estekak

0.70

出版年

0.67

OGND

0.67

 kasarigan

0.66

 Numerade

0.66

Personensuche

0.64

Activations Density 0.000%

numerical data related to television ratings

age demographic numbers

No Comments

No Known Activations