INDEX

Explanations

mentions of museums and related events

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.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>

-1.71

<?

-0.71

ⓧ

-0.68

/*++

-0.68

/**

-0.64

 intensify

-0.63

 provide

-0.63

 eliminate

-0.63

 fulfill

-0.62

 strode

-0.62

POSITIVE LOGITS

 Museum

1.89

 museum

1.85

Museum

1.82

 MUSEUM

1.67

 Museums

1.61

museum

1.60

Museums

1.60

 museums

1.53

Juf

1.33

 Museu

1.33

Activations Density 0.124%

mentions of museums and related events

No Comments

No Known Activations