INDEX

Explanations

actions related to reading and writing in a digital context

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

read, write, received, download, approved

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

weightedMode

-0.45

 Administrativna

-0.41

veau

-0.41

 Garment

-0.40

 FICTION

-0.40

 Vitamin

-0.39

duplicate

-0.38

 MINISTER

-0.38

vité

-0.37

 Verband

-0.37

POSITIVE LOGITS

 contextLoads

0.66

存于互联网档案馆

0.62

MLLoader

0.55

 مشين

0.51

قایناق‌لار

0.48

 EconPapers

0.48

};*/

0.47

 GenerationType

0.47

})*/

0.45

مصادر

0.45

Activations Density 0.099%

actions related to reading and writing in a digital context

read, write, received, download, approved

No Comments

No Known Activations