INDEX

Explanations

elements of positive experiences and events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Mitte

-0.56

 tall

-0.47

(/\

-0.46

 françaises

-0.45

lun

-0.45

мет

-0.45

<?

-0.45

 avanzada

-0.44

AlterField

-0.44

topus

-0.44

POSITIVE LOGITS

 AssemblyCompany

0.89

تقاوى

0.83

 eventful

0.81

 Roskov

0.81

évaluateur

0.78

SharedDtor

0.77

QMetaType

0.75

ंदीखरीदारी

0.75

contentLoaded

0.74

 kaarangay

0.74

Activations Density 0.234%

elements of positive experiences and events

No Comments

No Known Activations