INDEX

Explanations

phrases indicating popularity or significance of people, events, or topics

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

RenderAtEndOf

-0.60

enterOuterAlt

-0.56

TProtocol

-0.52

//

-0.51

 choses

-0.51

findpost

-0.50

 ***!

-0.48

 colpa

-0.48

 Politique

-0.48

DriverManager

-0.46

POSITIVE LOGITS

 attracts

0.69

 popular

0.67

 attracting

0.66

 attract

0.65

 Attra

0.65

 reputation

0.64

 popularity

0.62

 imageNamed

0.62

valuable

0.58

 notable

0.57

Activations Density 0.236%

phrases indicating popularity or significance of people, events, or topics

No Comments

No Known Activations