INDEX

Explanations

mentions of legal terms and court-related processes

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

 Everton

-0.71

 Bismarck

-0.69

 Maureen

-0.68

 Muske

-0.66

 Clare

-0.65

Everton

-0.64

 Mond

-0.63

Maureen

-0.62

 Munster

-0.60

 malin

-0.60

POSITIVE LOGITS

 Georgia

2.54

 Atlanta

2.35

Georgia

2.31

 GEORGIA

2.13

Atlanta

2.10

 georgia

1.96

 Georgian

1.93

 Tbilisi

1.83

georg

1.82

 Georg

1.74

Activations Density 0.371%

mentions of legal terms and court-related processes

No Comments

No Known Activations