INDEX

Explanations

mentions of capturing or taking control of something

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>

-3.38

ⓧ

-0.95

/**

-0.94

<?

-0.83

/***

-0.76

-0.74

 AssemblyCompany

-0.71

/*

-0.69

Kontrola

-0.68

/*!

-0.66

POSITIVE LOGITS

 lele

1.49

 saar

1.39

 stockholm

1.38

 dises

1.36

 ananas

1.36

 bandung

1.32

ohr

1.30

 Minang

1.29

 thuy

1.28

 levis

1.26

Activations Density 0.072%

mentions of capturing or taking control of something

No Comments

No Known Activations