INDEX

Explanations

phrases that express positive evaluations of performance or quality in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 RouterModule

-0.65

IBarButtonItem

-0.62

ISupport

-0.60

__(/*!

-0.60

 unknownFields

-0.58

 CanadaChoose

-0.56

 springfox

-0.53

Kreuz

-0.53

mobileqq

-0.53

 transférez

-0.51

POSITIVE LOGITS

########.

0.72

inerja

0.67

 cellpadding

0.64

BoxShadow

0.60

iarkan

0.59

 Arbeit

0.58

 Didi

0.57

findpost

0.57

мені

0.56

job

0.56

Activations Density 0.114%

phrases that express positive evaluations of performance or quality in various contexts

No Comments

No Known Activations