INDEX

Explanations

comments and documentation-related syntax 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 @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

errHandler

-0.81

 فريبيس

-0.55

MessageOf

-0.54

 AnyObject

-0.53

 Solidity

-0.53

Subview

-0.51

Ljava

-0.51

tling

-0.50

 Salford

-0.50

jface

-0.49

POSITIVE LOGITS

PreExecute

0.65

Tikang

0.63

enumi

0.60

__':

0.59

 estimés

0.58

 AssemblyTitle

0.56

ViewImports

0.54

ValueStyle

0.54

OGND

0.54

 interest

0.53

Activations Density 0.008%

comments and documentation-related syntax in code

No Comments

No Known Activations