INDEX

Explanations

references to specific events or performances

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>

-2.80

<?

-1.12

ⓧ

-1.00

-0.99

/**

-0.88

 intersper

-0.83

/*

-0.78

 quitted

-0.75

 rehabilitate

-0.74

 banish

-0.73

POSITIVE LOGITS

 karton

1.49

 silikon

1.42

 kafe

1.40

 keramik

1.38

 alkoh

1.29

 seksi

1.27

 kosme

1.26

uhr

1.25

 optik

1.16

 krim

1.16

Activations Density 0.068%

references to specific events or performances

No Comments

No Known Activations