INDEX

Explanations

elements related to UI components in programming

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

Code snippets and abbreviations

np_acts-logits-general · gemini-2.0-flash

electric locomotives; conviction should

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

Personendaten

-0.56

HideFlags

-0.54

ThemeOverlay

-0.53

<eos>

-0.52

addCriterion

-0.52

 betweenstory

-0.50

')):

-0.49

<bos>

-0.48

__*/

-0.48

POSITIVE LOGITS

enumii

0.72

 myſelf

0.72

SOB

0.67

esgue

0.67

EndInit

0.66

iD

0.65

WaitGroup

0.64

 itſelf

0.64

 ་་

0.63

multer

0.63

Activations Density 0.006%

elements related to UI components in programming

Code snippets and abbreviations

electric locomotives; conviction should

No Comments

No Known Activations