INDEX

Explanations

proper nouns, particularly names of places, organizations, and people

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

 space

-0.36

 alike

-0.35

 interesa

-0.34

 extraordinario

-0.34

 Osten

-0.33

 obligado

-0.33

 entendido

-0.32

 yürü

-0.32

 sveta

-0.32

SequentialGroup

-0.32

POSITIVE LOGITS

 Paglinawan

0.71

OGND

0.71

########.

0.62

ImageContext

0.59

 المعيارى

0.57

 Administrativna

0.54



0.54

$_(

0.54

 getSystem

0.53

 myſelf

0.53

Activations Density 0.031%

proper nouns, particularly names of places, organizations, and people

No Comments

No Known Activations