INDEX

Explanations

proper nouns, particularly names of individuals and families

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

:✨

-0.63

 esternos

-0.52

Personendaten

-0.50

featureID

-0.45

دانشنامهٔ

-0.44

InputBorder

-0.42

 consecu

-0.41

 Administrativna

-0.40

✨:

-0.40

UrlResolution

-0.40

POSITIVE LOGITS

 AssemblyCulture

0.52

Cartney

0.49

 family

0.44

 Infór

0.44

 familiares

0.43

 keluarga

0.43

yyr

0.42

 Democrá

0.40

 femenina

0.40

úrese

0.40

Activations Density 0.024%

proper nouns, particularly names of individuals and families

No Comments

No Known Activations