INDEX

Explanations

proper nouns and names, particularly related to people

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>

-2.92

/***

-0.85

<?

-0.84

///**

-0.78

<?

-0.71

ⓧ

-0.68

/*!

-0.63

 springfox

-0.62

/**

-0.61

POSITIVE LOGITS

 maneu

1.42

 impra

1.40

 unspeak

1.30

 shenan

1.27

 affor

1.23

 horrend

1.22

 increa

1.21

 Minang

1.17

 indescri

1.12

 gaily

1.11

Activations Density 0.397%

proper nouns and names, particularly related to people

No Comments

No Known Activations