INDEX

Explanations

references to a specific class or component in a programming context, particularly related to a factory pattern

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

 ویکی‌پدیا

-0.83

ConstraintMaker

-0.73

Personensuche

-0.72

Fordítás

-0.71

 argint

-0.63

opard

-0.62

virons

-0.62

();)

-0.62

Попис

-0.61

 calendriers

-0.61

POSITIVE LOGITS

Factory

0.68

no

0.51

 Park

0.51

IBAction

0.51

__':

0.50

leta

0.50

||

0.49

}',

0.49

 gema

0.49

pyplot

0.49

Activations Density 0.240%

references to a specific class or component in a programming context, particularly related to a factory pattern

No Comments

No Known Activations