INDEX

Explanations

expressions related to gratitude and thanking someone for their interest or visit

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.31

ⓧ

-0.77

/**

-0.73

<?

-0.72

EndProject

-0.71

ValueGenerated

-0.69

HasColumnType

-0.68

-0.67

💼

-0.66

HasAnnotation

-0.65

POSITIVE LOGITS

 embodi

1.56

 Keny

1.51

 Manufact

1.47

 accla

1.42

 sovere

1.39

 Intere

1.38

Juf

1.38

 impra

1.37

 Khart

1.36

 Minang

1.36

Activations Density 1.053%

expressions related to gratitude and thanking someone for their interest or visit

No Comments

No Known Activations