INDEX

Explanations

instances of the word "named" or its variations, indicating recognition or designation of individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MigrationBuilder

-0.70

 defaultstate

-0.64

 ―――――

-0.64

 Houſe

-0.63

 nahilalakip

-0.63

QMetaType

-0.62

NameInMap

-0.60

 Mezz

-0.60

 Marlene

-0.60

RegressionTest

-0.60

POSITIVE LOGITS

 named

2.83

named

2.64

 Named

2.62

Named

2.46

 nommé

1.46

 nommée

1.30

 naming

1.28

 nombrado

1.19

 Naming

1.11

naming

1.10

Activations Density 0.115%

instances of the word "named" or its variations, indicating recognition or designation of individuals or entities

No Comments

No Known Activations