INDEX

Explanations

detailed and intricate descriptions or features

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/***

-0.96

<bos>

-0.91

//{

-0.77

<?

-0.73

/**

-0.70

//};

-0.66

/**

-0.65

-0.64

BUYER

-0.62

<>

-0.61

POSITIVE LOGITS

 maneu

1.68

 elaborate

1.32

 strick

1.29

 impra

1.27

 shenan

1.26

 reluct

1.24

 stickied

1.20

 indulged

1.20

 indulging

1.18

 apprehen

1.16

Activations Density 0.291%

detailed and intricate descriptions or features

No Comments

No Known Activations