INDEX

Explanations

references to physical intimate contact, specifically kissing and hugging

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Economía

-0.62

 protoimpl

-0.61

Élet

-0.60

astéro

-0.60

Bakgrunnsstoff

-0.58

Atsauces

-0.57

Datuak

-0.55

pagni

-0.55

htiö

-0.54

TemporalType

-0.54

POSITIVE LOGITS

 shenan

1.37

 kiss

1.36

 kissing

1.36

 impra

1.35

 kissed

1.29

 unve

1.26

 maneu

1.25

 kisses

1.25

 unspeak

1.24

 Kiss

1.23

Activations Density 0.086%

references to physical intimate contact, specifically kissing and hugging

No Comments

No Known Activations