INDEX

Explanations

references to locations and educational institutions

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

GEBURTSDATUM

-0.66

rawDesc

-0.65

 Biôgrafia

-0.55

دانشنامهٔ

-0.53

 OMITBAD

-0.53

 contextLoads

-0.52

 otomatig

-0.50

 contactar

-0.50

iento

-0.49

存于互联网档案馆

-0.47

POSITIVE LOGITS

MessageState

0.41

book

0.40

 AssemblyCompany

0.36

MigrationBuilder

0.34

 book

0.34

 reti

0.34

 retrait

0.34

parsedMessage

0.32

LayoutInflater

0.32

 Camper

0.32

Activations Density 0.343%

references to locations and educational institutions

No Comments

No Known Activations