INDEX

Explanations

specific car models

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>

-2.28

ⓧ

-1.25

-1.19

<?

-1.05

 cabrio

-0.97

/**

-0.94

/***

-0.85

///**

-0.84

<?

-0.82

},[])

-0.78

POSITIVE LOGITS

 Heere

0.63

Ueb

0.62

 pubg

0.60

 Theile

0.59

 désol

0.59

 egreg

0.58

 Departement

0.58

 maneu

0.58

 impra

0.57

 lgbt

0.56

Activations Density 0.296%

specific car models

No Comments

No Known Activations