INDEX

Explanations

structured data representations, particularly in formats like lists or tables

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>

-3.15

 AssemblyCompany

-0.92

ⓧ

-0.83

/*

-0.76

/**

-0.76

HasIndex

-0.74

-0.70

TargetException

-0.59

PerformLayout

-0.59

<?

-0.59

POSITIVE LOGITS

 affor

1.30

 maroc

1.27

 philanth

1.25

 practition

1.23

 indestru

1.21

 maneu

1.17

 pollut

1.17

 Manufact

1.16

 unden

1.15

 inev

1.15

Activations Density 0.093%

structured data representations, particularly in formats like lists or tables

No Comments

No Known Activations