INDEX

Explanations

references to academic papers or publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 ModelExpression

-0.61

})();

-0.60

Voci

-0.54

 ويكيميديا

-0.54

خت

-0.54

}]);

-0.53

 ролях

-0.51

owohl

-0.51

Caratteristiche

-0.50

})();

-0.50

POSITIVE LOGITS

 CrossRef

0.69

CrossRef

0.58

ItemBackground

0.58

 kasarigan

0.55

bibitem

0.54

rungsseite

0.53

DataAnnotations

0.51

 jScrollPane

0.50

Geplaatst

0.48

 PubMed

0.48

Activations Density 0.952%

references to academic papers or publications

No Comments

No Known Activations