INDEX

Explanations

terms and phrases related to scientific measurements and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 AttributeSet

-0.70

 NSCoder

-0.68

 WebDriverWait

-0.64

 Infórmanos

-0.63

 neceff

-0.63

cein

-0.62

Cyfeiriadau

-0.60

IntoConstraints

-0.59

 Wiktionnaire

-0.58

ReusableCell

-0.58

POSITIVE LOGITS

Cro

1.01

Cru

0.99

cr

0.98

Cro

0.97

Cra

0.96

CR

0.94

cra

0.91

Cru

0.91

Cra

0.91

CR

0.88

Activations Density 2.959%

terms and phrases related to scientific measurements and evaluations

No Comments

No Known Activations