INDEX

Explanations

references to patients, users, and individuals in the context of healthcare and service interactions

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

 dAtA

-0.76

 tudo

-0.71

ignty

-0.67

///</

-0.65

 autorytatywna

-0.61

URLException

-0.59

igma

-0.58

itself

-0.58

 Crimes

-0.57

poons

-0.57

POSITIVE LOGITS

who

0.96

 clientèle

0.90

 patients

0.82

patients

0.79

 clients

0.75

 whom

0.73

 perſon

0.73

 passengers

0.73

 students

0.72

Innen

0.72

Activations Density 2.481%

references to patients, users, and individuals in the context of healthcare and service interactions

No Comments

No Known Activations