INDEX

Explanations

names and identifiers associated with individuals in legal cases

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

numerusform

-0.81

IsMutable

-0.81

XmlAccessType

-0.77

 calendriers

-0.76

 Olin

-0.72

 postales

-0.70

angor

-0.69

umumkan

-0.68

 Obrador

-0.68

 Itself

-0.66

POSITIVE LOGITS

concel

0.71

 Strö

0.61

Glej

0.61

 Jør

0.60

 Spra

0.60

 Ains

0.60

 Szab

0.58

 Alcal

0.58

 Catal

0.57

 McCa

0.57

Activations Density 0.096%

names and identifiers associated with individuals in legal cases

No Comments

No Known Activations