INDEX

Explanations

indicators of historical events and context

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

Holstein, Younger, genetic

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

 Inseln

-0.36

 Superan

-0.35

gesetzt

-0.34

Попис

-0.34

enido

-0.32

bzero

-0.32

 gunung

-0.30

정

-0.29

 piled

-0.29

 Meksiku

-0.29

POSITIVE LOGITS

存于互联网档案馆

0.80

ſehen

0.69

 パンチラ

0.66

ロウィン

0.66

 zuſammen

0.65

 erſt

0.64

 wiſſen

0.63

 ſehr

0.63

<unused55>

0.62

 ſeiner

0.62

Activations Density 0.028%

indicators of historical events and context

Holstein, Younger, genetic

No Comments

No Known Activations