INDEX

Explanations

references to expressions of gratitude or thanks

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.61

/**

-1.04

<?

-0.94

/***

-0.94

ⓧ

-0.92

-0.87

 intersper

-0.84

 endow

-0.81

///**

-0.78

 localize

-0.75

POSITIVE LOGITS

 marea

0.79

 Divulgação

0.69

 Comunicação

0.66

 véhic

0.65

 Gestão

0.64

 materie

0.63

 lavander

0.62

Literat

0.62

 Contribu

0.62

 Coloque

0.61

Activations Density 2.769%

references to expressions of gratitude or thanks

No Comments

No Known Activations