INDEX

Explanations

the word "rate" followed by a numerical value

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>

-3.29

-0.79

ⓧ

-0.69

<?

-0.68

///**

-0.67

/***

-0.66

/**

-0.61

/*

-0.59

<?

-0.58

 evacuate

-0.57

POSITIVE LOGITS

 quoique

1.29

 Rate

1.28

 Minang

1.26

 swarovski

1.24

 ricardo

1.24

 affor

1.23

 véhic

1.23

 Rates

1.22

 rate

1.21

 maneu

1.19

Activations Density 0.066%

the word "rate" followed by a numerical value

No Comments

No Known Activations