INDEX

Explanations

programming-related keywords and symbols, particularly in a Java or related coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 NUKAT

-0.62

GeneratedCode

-0.55

Pautan

-0.55

 invokingState

-0.52

<eos>

-0.49

 McNally

-0.47

kon

-0.46

 flow

-0.46

><!--

-0.45

POSITIVE LOGITS

CJK

0.74

 تانيه

0.74

 مشين

0.71

NUMX

0.71

mj

0.71

 whiteColor

0.70

 MatDialog

0.70

melons

0.69

UpInside

0.65

 UIFont

0.65

Activations Density 0.006%

programming-related keywords and symbols, particularly in a Java or related coding context

No Comments

No Known Activations