INDEX

Explanations

references to digital object identifiers (DOIs) and related citation formats

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

"doi" followed by a URL

np_acts-logits-general · gemini-2.0-flash

digital object identifier

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Rüyada

-0.55

 Италијани

-0.49

 useAppContext

-0.47

liesslich

-0.47

">

-0.45

 navideña

-0.45

⟬

-0.44

лтамалар

-0.44

ventilador

-0.43

emand

-0.42

POSITIVE LOGITS

doi

3.13

doi

2.27

DOI

1.89

DOI

1.80

Doi

1.50

Doi

1.45

CrossRef

1.18

出版年

0.93

orcid

0.76

 ModelExpression

0.74

Activations Density 0.197%

references to digital object identifiers (DOIs) and related citation formats

"doi" followed by a URL

digital object identifier

No Comments

No Known Activations