INDEX

Explanations

phrases that indicate safety or quality of something, especially in relation to functioning properly or performing well

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

occuper

-0.57

 interstitial

-0.56

ardless

-0.56

//

-0.56

tidaknya

-0.56

Invisible

-0.55

 čet

-0.55

opcional

-0.55

 Italijanski

-0.55

 lenker

-0.54

POSITIVE LOGITS

 initComponents

0.65

nade

0.59

:(

0.56

🙁

0.55

styleable

0.55

"]();

0.53

 MotionEvent

0.52

 MenuView

0.52

printStackTrace

0.50

 gron

0.49

Activations Density 0.466%

phrases that indicate safety or quality of something, especially in relation to functioning properly or performing well

No Comments

No Known Activations