INDEX

Explanations

dates within text

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.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>

-1.24

ⓧ

-0.84

<?

-0.75

public

-0.73

 enable

-0.71

/*

-0.69

enable

-0.69

ണ്ട

-0.68

 enhance

-0.67

/**

-0.66

POSITIVE LOGITS

 increa

2.12

 affor

2.10

 maneu

2.06

 impra

2.05

Juf

2.00

 philanth

1.89

 accla

1.88

 wherea

1.85

 guarante

1.83

 inev

1.83

Activations Density 0.096%

dates within text

No Comments

No Known Activations