INDEX

Explanations

code-related terminology and structure, particularly those associated with object-oriented programming and 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kháu

-0.56

 Offisielt

-0.54

Dowell

-0.53

حوال

-0.51

entación

-0.51

Advertisement

-0.49

RuleContext

-0.49

tionalität

-0.49

aarrggbb

-0.49

licone

-0.48

POSITIVE LOGITS

Datuak

0.64

ScopeManager

0.53

 mapStateToProps

0.50

 مخطط

0.48

()")

0.48

''')

0.48

новништво

0.47

 onCreateView

0.47

ImageIO

0.47

RectangleBorder

0.47

Activations Density 0.210%

code-related terminology and structure, particularly those associated with object-oriented programming and documentation

No Comments

No Known Activations