INDEX

Explanations

words enclosed in quotation marks at the beginning or end of a sentence

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.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

ⓧ

-1.35

<?

-1.24

-1.20

/**

-1.19

<?

-1.08

/***

-1.06

/*

-1.00

<bos>

-0.92

/*!

-0.87

 springfox

-0.84

POSITIVE LOGITS

 affor

1.54

 maneu

1.51

 accla

1.36

 increa

1.31

 impra

1.27

 véhic

1.27

 opport

1.25

 fortn

1.24

 Intere

1.23

 wherea

1.21

Activations Density 1.227%

words enclosed in quotation marks at the beginning or end of a sentence

No Comments

No Known Activations