INDEX

Explanations

questions and answers related to inquiry within a dialogue context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 SafeMath

-0.67

felf

-0.66

SerializedSize

-0.65

 StyleSheet

-0.64

 AppModule

-0.64

ंदीखरीदारी

-0.64

Amicalement

-0.63

 Lightboxes

-0.63

NUMX

-0.62

Importante

-0.62

POSITIVE LOGITS

Are

0.60

What

0.56

Are

0.56

How

0.54

Do

0.52

how

0.52

 Quels

0.52

Is

0.52

 what

0.51

 telefónica

0.51

Activations Density 0.105%

questions and answers related to inquiry within a dialogue context

No Comments

No Known Activations