INDEX

Explanations

references to destruction and violence in historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

jspx

-0.64

 betweenstory

-0.58

tvguidetime

-0.53

 Réponses

-0.52

ImageContext

-0.49

 bağlantılar

-0.49

DateTimeFormat

-0.48

elcome

-0.48

 handleClick

-0.47

RTCF

-0.47

POSITIVE LOGITS

 destruction

1.53

 destroyed

1.50

 destroy

1.34

 destroying

1.29

 Destruction

1.28

 Destroy

1.25

destruction

1.23

 destroys

1.23

 damage

1.18

destroyed

1.16

Activations Density 0.367%

references to destruction and violence in historical contexts

No Comments

No Known Activations