INDEX

Explanations

specialized terms and phrases related to technical or scientific contexts

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

Text after questions or introductory phrases

np_acts-logits-general · gemini-2.0-flash

common choice

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

GraphicsUnit

-0.84

featureID

-0.73

 ddelweddau

-0.70

ViewFeatures

-0.63

tagHelperRunner

-0.58

__*/

-0.55

Instances

-0.54

 odkazy

-0.54

ExtendWith

-0.53

 الرياضيه

-0.53

POSITIVE LOGITS

 content

0.60

 what

0.55

 contents

0.53

 choice

0.51

 pattern

0.50

 initial

0.50

स्तु

0.49

 shape

0.48

 choices

0.47

是什么

0.47

Activations Density 0.651%

specialized terms and phrases related to technical or scientific contexts

Text after questions or introductory phrases

common choice

No Comments

No Known Activations