INDEX

Explanations

numerical values and mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.17.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

 vectorielle

-0.71

adaptiveStyles

-0.71

 originais

-0.70

 feroit

-0.69

 sagesse

-0.68

 föres

-0.66

 TAMBÉM

-0.66

 ſaid

-0.65

 contratto

-0.65

 femininas

-0.65

POSITIVE LOGITS

abestanden

0.69

 Administrativna

0.54

انجليز

0.52

XmlEnum

0.52

 Black

0.52

IBOutlet

0.52

 поводу

0.52

その他

0.51

<eos>

0.51

Activations Density 0.221%

numerical values and mathematical expressions

No Comments

No Known Activations