INDEX

Explanations

phrases related to characteristics and qualities of individuals, particularly focusing on impressive qualities

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

fup

-1.66

ftu

-1.66

fta

-1.65

 wien

-1.65

 sovere

-1.58

fte

-1.58

Juf

-1.58

 thut

-1.57

 seiz

-1.53

 practition

-1.52

POSITIVE LOGITS

 traits

0.70

 trait

0.63

trait

0.63

traits

0.61

 qualities

0.60

Traits

0.58

 attribute

0.57

ariConfig

0.56

MENAFN

0.55

Trait

0.55

Activations Density 0.500%

phrases related to characteristics and qualities of individuals, particularly focusing on impressive qualities

No Comments

No Known Activations