INDEX

Explanations

words related to nursing responsibilities and healthcare frameworks

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

preceding estimated, improve, maintain, or release

np_acts-logits-general · gemini-2.0-flash

care pathways

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Aussie

-0.74

 Apparently

-0.68

 goddamn

-0.68

Apparently

-0.66

 amerik

-0.66

 вроде

-0.65

 civilisation

-0.65

 supposedly

-0.64

 tranny

-0.64

 whatnot

-0.63

POSITIVE LOGITS

@"/

0.72

sproz

0.68

 nationally

0.67

emplar

0.61

OrNil

0.60

tipation

0.60

 nationaux

0.59

rancy

0.58

}))

0.57

Personensuche

0.56

Activations Density 0.270%

words related to nursing responsibilities and healthcare frameworks

preceding estimated, improve, maintain, or release

care pathways

No Comments

No Known Activations