INDEX

Explanations

locations or places within a setting

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

<bos>

-2.19

ⓧ

-1.27

/**

-1.24

-1.18

<?

-1.02

/*

-1.01

новништво

-1.01

/***

-1.00

<?

-0.97

///**

-0.92

POSITIVE LOGITS

 maneu

1.38

 accla

1.07

 impra

1.04

 affor

1.04

 disagre

1.02

 fortn

1.01

 épu

1.01

 véhic

1.00

Juf

0.99

 increa

0.98

Activations Density 0.826%

locations or places within a setting

No Comments

No Known Activations