INDEX

Explanations

locations or directions in the context of navigating a website interface

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>

-3.40

ⓧ

-0.89

/*

-0.83

<?

-0.83

/***

-0.76

/**

-0.73

//{

-0.71

})();

-0.65

 promote

-0.63

POSITIVE LOGITS

 maneu

2.08

 affor

1.98

 reluct

1.88

 impra

1.80

 increa

1.73

 disagre

1.73

 shenan

1.73

 unlaw

1.70

 excru

1.69

 accla

1.68

Activations Density 0.148%

locations or directions in the context of navigating a website interface

No Comments

No Known Activations