INDEX

Explanations

legal terminology and references to court decisions or judicial rulings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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



-0.50

 ativo

-0.47

srcs

-0.44

ิด

-0.44

 remercie

-0.43

िखित

-0.43

Closeable

-0.42

 thanking

-0.42

 activo

-0.42

usda

-0.41

POSITIVE LOGITS

 disputes

1.18

 adjud

1.15

 adjudication

1.12

 dispute

1.12

 Disputes

1.07

 rulings

1.01

 Determining

1.00

 determining

0.99

Determining

0.99

 determination

0.96

Activations Density 0.828%

legal terminology and references to court decisions or judicial rulings

No Comments

No Known Activations