INDEX

Explanations

references to individuals and their relationships with others, often highlighting their roles within a family or social context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 husbands

-0.93

MessageTagHelper

-0.92

 male

-0.89

Male

-0.87

 متعلقه

-0.86

 males

-0.85

Personendaten

-0.82

 Male

-0.82

 mascul

-0.79

 männ

-0.78

POSITIVE LOGITS

 widow

0.64

 sorcer

0.62

 wife

0.61

 propriet

0.55

 mother

0.52

 beautiful

0.51

 enchant

0.51

 Propriet

0.51

 stepmother

0.49

 bellissima

0.49

Activations Density 0.285%

references to individuals and their relationships with others, often highlighting their roles within a family or social context

No Comments

No Known Activations