INDEX

Explanations

references to factory or class instantiations in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

@"/

-0.64

énario

-0.62

تقاوى

-0.58

 تضيفلها

-0.57

 نف

-0.57

postIndex

-0.56

 defaultstate

-0.55

Synd

-0.54

igue

-0.54

}^{+\

-0.53

POSITIVE LOGITS

Factory

0.76

pool

0.76

 connexes

0.67

에

0.65

 للمعارف

0.63

POOL

0.61

Pool

0.61

RectangleBorder

0.61

 barnen

0.59

 indisponible

0.59

Activations Density 0.051%

references to factory or class instantiations in programming contexts

No Comments

No Known Activations