INDEX

Explanations

phrases related to decision-making and standards

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.21

ⓧ

-0.83

<?

-0.81

/**

-0.78

HttpDelete

-0.77

-0.74

-0.71

addGroup

-0.68

/*!

-0.68

POSITIVE LOGITS

 maneu

1.88

 increa

1.81

 impra

1.80

 milf

1.79

 affor

1.77

 hairc

1.75

 strick

1.67

 disagre

1.67

 ?...

1.66

 accla

1.65

Activations Density 0.327%

phrases related to decision-making and standards

No Comments

No Known Activations