INDEX

Explanations

references to judges or judicial positions in the text

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 poto

-0.78

vay

-0.61

 fjor

-0.59

 parut

-0.59

 boletín

-0.58

Carn

-0.58

 bocas

-0.57

ing

-0.56

త్

-0.56

 عام

-0.56

POSITIVE LOGITS

 Judges

1.22

JUDGE

1.18

 JUDGE

1.16

 judges

1.10

Judges

1.05

Judge

0.96

 Judge

0.96

 InputDecoration

0.90

BoxShadow

0.89

MigrationBuilder

0.86

Activations Density 0.014%

references to judges or judicial positions in the text

No Comments

No Known Activations

references to judges or judicial positions in the text

No Comments

No Known Activations