INDEX

Explanations

significant overall assessments or ratings in the text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.53

/***

-0.80

<?

-0.71

///**

-0.66

/*!

-0.64

/**

-0.62

//---

-0.61

<!--

-0.57

 assistir

-0.57

 consult

-0.56

POSITIVE LOGITS

 Minang

1.39

 perfon

1.29

 lidl

1.28

 bandung

1.28

 chrysler

1.27

 stockholm

1.24

 Palembang

1.24

 Karang

1.22

 embodi

1.19

 jaya

1.19

Activations Density 0.056%

significant overall assessments or ratings in the text

No Comments

No Known Activations