INDEX

Explanations

criteria for non-discrimination and equal opportunities based on traits like race, gender, sexual orientation, and disability

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

ⓧ

-1.06

-0.93

/**

-0.90

<?

-0.87

/*

-0.83

/*++

-0.77

<?

-0.77

 find

-0.71

<!--

-0.70

POSITIVE LOGITS

Juf

1.70

 Minang

1.67

 stockholm

1.61

aen

1.60

 bandung

1.59

 dises

1.58

 riviera

1.53

 thut

1.53

 Augu

1.53

 maer

1.53

Activations Density 0.062%

criteria for non-discrimination and equal opportunities based on traits like race, gender, sexual orientation, and disability

No Comments

No Known Activations