INDEX

Explanations

references to courts and judicial proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

rungsseite

-1.02

gangenen

-0.70

 Pedersen

-0.69

 Kelle

-0.69

isal

-0.69

 connexes

-0.68

 iParam

-0.67

principalTable

-0.66

 paja

-0.66

PositiveButton

-0.65

POSITIVE LOGITS

 Court

1.71

 Courts

1.52

 COURT

1.50

 court

1.48

Court

1.40

 courts

1.39

court

1.38

COURT

1.34

courts

1.28

 COUR

1.21

Activations Density 0.128%

references to courts and judicial proceedings

No Comments

No Known Activations