INDEX

Explanations

certain categories or classifications of content, such as editorial columns, commencement ceremonies, and op-eds

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.08

ⓧ

-1.02

/**

-0.93

-0.89

<?

-0.84

/***

-0.79

///**

-0.75

/*

-0.74

Transcripción

-0.61

/*!

-0.60

POSITIVE LOGITS

 Minang

0.86

 thuy

0.86

 Palembang

0.78

 yong

0.75

 Somal

0.72

 maroc

0.72

 montagna

0.72

 Tanjung

0.71

 Juventud

0.71

 Czechos

0.71

Activations Density 0.803%

certain categories or classifications of content, such as editorial columns, commencement ceremonies, and op-eds

No Comments

No Known Activations