INDEX

Explanations

class definitions and inheritance keywords in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Constitucional

-0.59

-0.57

elemField

-0.56

SerializedSize

-0.55

PreferredItem

-0.55

 Económica

-0.54

ItemLayout

-0.54

ClientRect

-0.54

 BitmapFactory

-0.53

 mohair

-0.53

POSITIVE LOGITS

帖最后由

1.18

offsetof

0.73

enumi

0.72

 ActionResult

0.72

fjspx

0.67

 class

0.67

enumii

0.67

것은

0.67

]$}

0.66

},[])

0.65

Activations Density 0.022%

class definitions and inheritance keywords in code

No Comments

No Known Activations