INDEX

Explanations

technical terms and phrases related to legal and scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ItemBackground

-0.89

دانشنامهٔ

-0.86

 متعلقه

-0.85

 Roskov

-0.85

CodedInputStream

-0.83

XmlAccessorType

-0.82

PreferredItem

-0.79

 חיצוניים

-0.78

Referencie

-0.77

 disambiguazione

-0.73

POSITIVE LOGITS

 تضيفلها

0.44

dry

0.43

 sequence

0.42

 already

0.42

seiti

0.40

arbe

0.39

 строй

0.37

 démarche

0.37

绝

0.37

 détour

0.36

Activations Density 1.422%

technical terms and phrases related to legal and scientific contexts

No Comments

No Known Activations