INDEX

Explanations

terms related to fairness or equity

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>

-3.00

-0.93

ⓧ

-0.85

/*++

-0.69

/**

-0.69

lateinit

-0.68

<?

-0.68

/*

-0.66

 interact

-0.64

 develop

-0.63

POSITIVE LOGITS

 bandung

1.51

 maroc

1.48

 Minang

1.47

 casio

1.36

 quoc

1.35

cæ

1.35

 nuoc

1.34

 napoli

1.34

 brava

1.34

 tramont

1.34

Activations Density 0.078%

terms related to fairness or equity

No Comments

No Known Activations