INDEX

Explanations

technical information or 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>

-3.23

ⓧ

-1.13

<?

-0.96

-0.92

/***

-0.88

/**

-0.88

///**

-0.84

/*

-0.72

<?

-0.70

EndGlobalSection

-0.69

POSITIVE LOGITS

 affor

1.36

 maneu

1.30

 accla

1.26

 increa

1.21

 volunte

1.16

 véhic

1.15

 fortn

1.13

 opport

1.13

 reluct

1.12

 impra

1.10

Activations Density 0.345%

technical information or instructions

No Comments

No Known Activations