INDEX

Explanations

technical terms and attributes related to software components and assemblies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

glise

-0.60

ocardium

-0.51

datei

-0.50

onames

-0.49

calipsis

-0.47

 suaminya

-0.47

MathML

-0.47

ometal

-0.47

RenderAtEndOf

-0.47

raszam

-0.46

POSITIVE LOGITS

脚注の使い方

0.73

 BoxDecoration

0.72

 שוליים

0.71

 PackageManager

0.67

rod

0.66

PerformLayout

0.66

EndInit

0.64

OGND

0.64

IntoConstraints

0.64

})));

0.64

Activations Density 2.973%

technical terms and attributes related to software components and assemblies

No Comments

No Known Activations