INDEX

Explanations

compound words prefixed with "comp" or variations of the word "compounding."

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>

-2.61

 intersper

-0.99

 endow

-0.95

/**

-0.94

/***

-0.94

 disbur

-0.89

ⓧ

-0.88

<?

-0.87

-0.85

/*!

-0.80

POSITIVE LOGITS

 Comp

1.39

 saar

1.28

Comp

1.22

 COMP

1.17

 saad

1.17

 comp

1.14

comp

1.08

 komp

1.06

COMP

1.06

 kompres

1.04

Activations Density 0.141%

compound words prefixed with "comp" or variations of the word "compounding."

No Comments

No Known Activations