INDEX

Explanations

descriptions related to hat features, materials, and care instructions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.71

-0.92

ⓧ

-0.79

<?

-0.79

<?

-0.68

/**

-0.65

/***

-0.65

paddingVertical

-0.63

bigsqcup

-0.62

</>

-0.62

POSITIVE LOGITS

Hat

1.38

Hat

1.37

Hats

1.30

HAT

1.29

 hats

1.25

hat

1.24

 Hats

1.24

 Hatt

1.19

HAT

1.12

 maneu

0.98

Activations Density 0.109%

descriptions related to hat features, materials, and care instructions

No Comments

No Known Activations