INDEX

Explanations

mathematical or scientific notation and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 AssemblyProduct

-0.76

providedIn

-0.73

AnchorStyles

-0.67

XmlAccessType

-0.66

 مرئيه

-0.65

δες

-0.64

EndProject

-0.64

)++;

-0.64

 незавершена

-0.62

 &___

-0.60

POSITIVE LOGITS

,...

0.60

,<

0.58

QMetaType

0.57

0.56

,=

0.55

 kasarigan

0.54

,[

0.52

,',

0.52

BindView

0.52

 faptul

0.52

Activations Density 0.516%

mathematical or scientific notation and symbols

No Comments

No Known Activations

mathematical or scientific notation and symbols

No Comments

No Known Activations