INDEX

Explanations

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tertentu

-0.49

Personensuche

-0.44

 علیه

-0.44

 TestBed

-0.44

PROG

-0.43

 generales

-0.43

יצד

-0.42

älv

-0.41

 mía

-0.40

esterno

-0.40

POSITIVE LOGITS

migrationBuilder

0.94

EndInit

0.91

AutoScale

0.89

CloseOperation

0.75

abestanden

0.73

 autorytatywna

0.71

 AttributeSet

0.69

 reminding

0.68

HomeAsUpEnabled

0.67

 kindly

0.67

Activations Density 0.070%

expressions of gratitude and appreciation

No Comments

No Known Activations