INDEX

Explanations

phrases related to sports seasons and related activities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.49

ⓧ

-0.96

///**

-0.78

/***

-0.76

public

-0.75

/**

-0.73

/*

-0.70

-0.69

/**

-0.68

<?

-0.67

POSITIVE LOGITS

 season

1.71

 stockholm

1.63

 Season

1.61

 affor

1.58

Season

1.58

 SEASON

1.56

 Minang

1.51

 wien

1.49

Juf

1.49

 jaya

1.48

Activations Density 0.135%

phrases related to sports seasons and related activities

No Comments

No Known Activations