INDEX

Explanations

references to monuments and memorials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 protoimpl

-0.71

DispatchToProps

-0.52

ressible

-0.50

Paper

-0.50

évaluateur

-0.50

 Paper

-0.49

 twill

-0.47

 pajamas

-0.47

PAPER

-0.47

POSITIVE LOGITS

 statue

1.62

 monument

1.57

 statues

1.48

 sculpture

1.38

 monuments

1.33

statue

1.30

 memorial

1.28

 sculptures

1.24

 Monument

1.24

Statue

1.19

Activations Density 0.161%

references to monuments and memorials

No Comments

No Known Activations