INDEX

Explanations

mentions of relatives, especially nieces and nephews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

InputBorder

-0.74

 Préférences

-0.68

 متعلقه

-0.68

rungsseite

-0.67

 parental

-0.67

 دیکھیے

-0.66

 Parental

-0.65

Історія

-0.65

 antic

-0.64

 Mommy

-0.63

POSITIVE LOGITS

 nephews

2.58

 nieces

2.56

 nephew

1.90

 niece

1.83

 grandchildren

1.25

 grandsons

1.06

 granddaughter

1.05

 grandson

1.04

 grandkids

1.02

甥

0.97

Activations Density 0.072%

mentions of relatives, especially nieces and nephews

No Comments

No Known Activations