INDEX

Explanations

references to official processes or documentation

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

 étoit

-0.71

 étoient

-0.67

 pouvoit

-0.65

WebVitals

-0.63

 auroit

-0.62

 sauvages

-0.62

 télévis

-0.60

 gouver

-0.60

 meurt

-0.60

initComponents

-0.59

POSITIVE LOGITS

">//

0.59

 فريبيس

0.52

interopRequire

0.49

'])->

0.48

Hozzáférés

0.48

 Dorado

0.48

toPromise

0.47

 RemoteException

0.46

enix

0.44

ibatis

0.44

Activations Density 0.689%

references to official processes or documentation

No Comments

No Known Activations