INDEX

Explanations

phrases related to technical explanations and instructions

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>

-2.85

ⓧ

-1.00

<?

-0.93

-0.83

/***

-0.76

/**

-0.73

/*

-0.67

///**

-0.64

Kontrola

-0.61

 deliver

-0.60

POSITIVE LOGITS

 maneu

1.56

 wien

1.38

 disagre

1.38

 stockholm

1.37

 accla

1.37

 impra

1.33

 increa

1.32

 reluct

1.30

 disreg

1.30

 bandung

1.28

Activations Density 0.046%

phrases related to technical explanations and instructions

No Comments

No Known Activations