INDEX

Explanations

language and terms associated with legal and regulatory contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

kjø

-0.50

colgante

-0.47

 OFDb

-0.47

 culturelle

-0.46

 Vereinbarung

-0.46

occasione

-0.44

endroit

-0.44

ContentAsync

-0.44

 quedaba

-0.43

 mainan

-0.41

POSITIVE LOGITS

MigrationBuilder

0.55

 disambiguazione

0.46

GEBURTSDATUM

0.44

 препратки

0.42

reactstrap

0.40

 محفوظة

0.40

JAXB

0.38

 jLabel

0.38

 setText

0.38

CloseOperation

0.37

Activations Density 0.102%

language and terms associated with legal and regulatory contexts

No Comments

No Known Activations