INDEX

Explanations

references to the term "Gen" or its variations, likely indicating a focus on specific organizations or entities

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

})();

-0.56

barer

-0.54

ябрь

-0.53

barkeit

-0.50

*/}

-0.50

 ölüm

-0.48

 XCTest

-0.48

csolódó

-0.47

顿

-0.47

TERA

-0.47

POSITIVE LOGITS

Gen

1.05

Gen

0.84

featureID

0.81

 shade

0.78

脚注の使い方

0.78

PyExc

0.74

ніципалі

0.73

SerializedSize

0.71

 ujednoznacz

0.71

 odkazy

0.69

Activations Density 0.082%

references to the term "Gen" or its variations, likely indicating a focus on specific organizations or entities

No Comments

No Known Activations