INDEX

Explanations

various terms related to neurology and its subfields

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

"neuro"

np_acts-logits-general · gemini-2.0-flash

neuro prefix in medical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

ValueStyle

-0.56

 noDo

-0.56

RenderAtEndOf

-0.55

NameInMap

-0.54

 ExecuteAsync

-0.52

}{@

-0.52

 CreateTagHelper

-0.52

tagHelperRunner

-0.48

Tembelea

-0.48

ViewFeatures

-0.47

POSITIVE LOGITS

 neuro

0.73

 Neuro

0.65

Neuro

0.60

neuro

0.56

 nervous

0.53

Neu

0.49

 neural

0.48

Neu

0.48

 nerve

0.47

neu

0.47

Activations Density 0.093%

various terms related to neurology and its subfields

"neuro"

neuro prefix in medical terms

No Comments

No Known Activations