INDEX

Explanations

expressions related to feelings of embarrassment, shame, or regret

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

OGND

-0.71

Nuorodos

-0.61

 bunda

-0.61

StartPosition

-0.61

 meras

-0.57

paddingVertical

-0.56

marginVertical

-0.56

Voci

-0.52

 Ressources

-0.51

 teng

-0.50

POSITIVE LOGITS

 embarrassed

0.98

 embarrassment

0.98

 Embar

0.91

 embarrass

0.90

 embarrassing

0.90

 shame

0.86

 ashamed

0.85

 shameful

0.82

 Shame

0.80

 humiliated

0.79

Activations Density 0.126%

expressions related to feelings of embarrassment, shame, or regret

No Comments

No Known Activations