INDEX

Explanations

code-related syntax, particularly in programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 StatefulWidget

-0.66

ResumeLayout

-0.53

 StatelessWidget

-0.50

Pranala

-0.50

SpringBootTest

-0.49

forKey

-0.48

++

-0.47

tac

-0.46

كونات

-0.45

 bridge

-0.45

POSITIVE LOGITS

 kasarigan

0.66

ыгана

0.64

msgTypes

0.62

Tembelea

0.62

 Савезне

0.61

featureID

0.61

 JpaRepository

0.60

GeneratedValue

0.58

LookAnd

0.57

Grüsse

0.56

Activations Density 0.200%

code-related syntax, particularly in programming languages

No Comments

No Known Activations