INDEX

Explanations

legal terms and actions related to court proceedings and verdicts

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

Tokens preceding or related to "verdict"

np_acts-logits-general · gemini-2.0-flash

guilty verdict

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/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.24.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

Datuak

-0.66

SharedDtor

-0.63

 autorytatywna

-0.57

ếp

-0.56

 internetowa

-0.54

 <<<<<<<<<<<<<<

-0.53

 arrests

-0.52

 arresting

-0.52

 reprints

-0.51

المناصب

-0.50

POSITIVE LOGITS

 guilty

1.01

 verdict

0.93

 Guilty

0.89

 verdicts

0.83

Guilty

0.83

 finding

0.79

guilty

0.78

 Verdict

0.77

 jury

0.76

Verdict

0.76

Activations Density 1.411%

legal terms and actions related to court proceedings and verdicts

Tokens preceding or related to "verdict"

guilty verdict

No Comments

No Known Activations