INDEX

Explanations

references to IntelliJ and related programming terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

 Мексичка

-0.86

fjspx

-0.83

orianCalendar

-0.79

DoubleQuotes

-0.78

 للاسماء

-0.78

ientôt

-0.72

 يتيمه

-0.72

 gynnwys

-0.69

 MemoryStream

-0.68

."],

-0.67

POSITIVE LOGITS

Pyx

1.76

LabelTagHelper

0.78

tagHelperRunner

0.73

mml

0.70

NullCheck

0.69

AndEndTag

0.67

 wireType

0.63

 חיצוניים

0.60

DataAnnotations

0.58

CrossRef

0.57

Activations Density 0.011%

references to IntelliJ and related programming terms

No Comments

No Known Activations