INDEX

Explanations

mathematical expressions and notations related to linear algebra and statistical estimators

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Hiper

-0.51

passo

-0.50

andidates

-0.48

paigns

-0.48

 Sides

-0.47

 başar

-0.46

imensional

-0.46

 flaps

-0.46

bounding

-0.45

 passagers

-0.45

POSITIVE LOGITS

bootstrapcdn

0.77

GroupLayout

0.71

 initComponents

0.66

 QtCore

0.65

тьяна

0.64

WebElementEntity

0.63

InjectAttribute

0.63

Derbyniad

0.62

 oprot

0.60

 الحره

0.60

Activations Density 0.612%

mathematical expressions and notations related to linear algebra and statistical estimators

No Comments

No Known Activations