INDEX

Explanations

references to individuals or entities, particularly in contexts related to relationships and legal matters

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

 estekak

-0.71

 Administrativna

-0.56

 protoimpl

-0.55

]=>

-0.54

лтемелер

-0.54

 tartalomajánló

-0.52

 kasarigan

-0.52

 समीक्षाओं

-0.52

XmlAccessType

-0.50

 esternos

-0.50

POSITIVE LOGITS

ⓧ

0.49

 CreateTagHelper

0.40

rungsseite

0.39

 autorytatywna

0.38

URLEncoder

0.36

허

0.35

รง

0.35

YSQL

0.34

itself

0.34

ựu

0.34

Activations Density 0.384%

references to individuals or entities, particularly in contexts related to relationships and legal matters

No Comments

No Known Activations