INDEX

Explanations

keywords related to legal terminology and judicial processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

-0.59

Gambas

-0.56

LOGY

-0.56

chowa

-0.55

FieldNumber

-0.54

ւ

-0.52

</tr>

-0.51

intă

-0.51

)))))

-0.51

eraard

-0.50

POSITIVE LOGITS

évaluateur

0.89

 المعيارى

0.73

 للمعارف

0.72

<bos>

0.58

\{\\

0.58

.*")]

0.55

 Zacks

0.54

 وتسجيلات

0.53

 Vork

0.52

 فريبيس

0.51

Activations Density 2.567%

keywords related to legal terminology and judicial processes

No Comments

No Known Activations