INDEX

Explanations

phrases related to violent and unsettling content

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

 fonder

-0.60

 kredi

-0.59

 Strukt

-0.56

 oner

-0.55

 Meksi

-0.53

 mémor

-0.52

 Româ

-0.51

iloj

-0.51

 Portugu

-0.50

 vété

-0.50

POSITIVE LOGITS

 respectively

0.59

]='\

0.52

 виправивши

0.50

 thereupon

0.49

aarrggbb

0.48

respectively

0.48

lepiej

0.48

 thereunder

0.48

ļ

0.47

 endeavoured

0.47

Activations Density 0.735%

phrases related to violent and unsettling content

No Comments

No Known Activations