INDEX

Explanations

terms related to political power dynamics and capabilities

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>

-2.14

-0.73

 enshr

-0.72

 inaugurate

-0.69

/**

-0.68

 harmonize

-0.68

ⓧ

-0.64

 abolish

-0.64

 reunite

-0.63

<?

-0.62

POSITIVE LOGITS

 paradiso

1.27

 soggior

1.10

 bandung

1.08

 riva

1.03

 megane

1.02

 venuto

0.96

 toscana

0.95

!!</

0.95

 lele

0.95

 eiffel

0.95

Activations Density 0.292%

terms related to political power dynamics and capabilities

No Comments

No Known Activations