INDEX

Explanations

mentions of specific organizations or medical terms related to healthcare roles

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

Follows "Q:" or contains code/technical terms

np_acts-logits-general · gemini-2.0-flash

Q:

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Dink

-0.55

↵↵

-0.54

󠁢

-0.54

GEBURTSDATUM

-0.53

 […]

-0.51

-0.50

↵

-0.48

 prow

-0.47

wow

-0.47

</h5>

-0.45

POSITIVE LOGITS

 ModelExpression

0.83

存于互联网档案馆

0.79

Архівовано

0.78

jspx

0.74

bootstrapcdn

0.70

)':

0.69

 metav

0.69

}');

0.68

Koordinaten

0.68

.")

0.68

Activations Density 0.040%

mentions of specific organizations or medical terms related to healthcare roles

Follows "Q:" or contains code/technical terms

Q:

No Comments

No Known Activations