INDEX

Explanations

abbreviations or acronyms related to specific individuals or organizations

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>

-2.61

ⓧ

-1.26

/***

-0.97

<?

-0.97

/**

-0.80

 ProtoMessage

-0.80

 solidar

-0.80

/*!

-0.78

///**

-0.77

 intptr

-0.76

POSITIVE LOGITS

 impra

1.09

 soulign

1.07

 véhic

1.03

 affor

0.99

 maneu

0.98

 considér

0.98

 Manufact

0.96

 pleins

0.94

 unlaw

0.92

Byp

0.92

Activations Density 0.022%

abbreviations or acronyms related to specific individuals or organizations

No Comments

No Known Activations