INDEX

Explanations

technical terminology and measurements relevant to scientific processes and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Viited

-0.64

Искәрмәләр

-0.55

HtmlAttribute

-0.55

styleType

-0.53

EDEFAULT

-0.53

脚注の使い方

-0.51

Gambas

-0.49

ChildScrollView

-0.44

archar

-0.44

instancetype

-0.44

POSITIVE LOGITS

 helps

1.83

 enables

1.67

helps

1.49

 gives

1.48

 allows

1.48

 ensures

1.47

ทำให้

1.45

 Helps

1.45

 helped

1.44

 makes

1.40

Activations Density 2.253%

technical terminology and measurements relevant to scientific processes and outcomes

No Comments

No Known Activations