INDEX

Explanations

references to legal terminology and context related to lawsuits and court 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

 تضيفلها

-1.18

 Tamara

-1.02

Tamara

-0.97

logr

-0.94

 Copernicus

-0.90

STS

-0.89

 propOrder

-0.85

 anorexia

-0.85

 Wilber

-0.84

gira

-0.84

POSITIVE LOGITS

<?=$

0.96

asive

0.75

 Dickerson

0.75

/"+

0.73

 Dunkel

0.71

ား

0.71

الحياه

0.69

 خص

0.68

"],

0.68

../

0.67

Activations Density 1.772%

references to legal terminology and context related to lawsuits and court proceedings

No Comments

No Known Activations