INDEX

Explanations

references, citations, and structured data typically used in academic articles

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

 ddelweddau

-0.71

 دیکھیے

-0.68

XmlAccessType

-0.67

 '\\;'

-0.62

AccessFile

-0.59

 iprot

-0.58

存于互联网档案馆

-0.57

 архивлан

-0.57

Få

-0.56

}")]

-0.55

POSITIVE LOGITS

</thead>

0.52

gehalt

0.49

 trung

0.47

berton

0.47

 الحره

0.45

 liberty

0.45

ウェル

0.44

中の

0.44

AxisAlignment

0.43

MigrationBuilder

0.42

Activations Density 0.138%

references, citations, and structured data typically used in academic articles

No Comments

No Known Activations