INDEX

Explanations

specific business or organization-related terms and contact information

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>

-1.49

-0.93

<?

-0.92

/**

-0.88

-0.87

to

-0.84

can

-0.83

are

-0.83

 would

-0.82

POSITIVE LOGITS

 meis

1.85

 Minang

1.83

 applau

1.83

ftu

1.79

 fatis

1.76

 nece

1.75

 lele

1.72

cæ

1.70

 dises

1.69

fup

1.69

Activations Density 3.591%

specific business or organization-related terms and contact information

No Comments

No Known Activations