INDEX

Explanations

words related to website content such as terms like "side effects," "bars," and "product information."

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>

-3.12

<?

-0.85

/***

-0.81

-0.80

ⓧ

-0.79

<?

-0.79

/**

-0.71

/*

-0.71

//{

-0.71

HasIndex

-0.70

POSITIVE LOGITS

aen

1.30

ftu

1.25

fta

1.22

 affor

1.20

 Side

1.18

mef

1.17

 ftre

1.17

 stockholm

1.17

 foon

1.16

fup

1.16

Activations Density 0.164%

words related to website content such as terms like "side effects," "bars," and "product information."

No Comments

No Known Activations