INDEX

Explanations

references to historical or academic figures and institutions

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>

-3.21

/**

-0.88

ⓧ

-0.86

 springfox

-0.83

<?

-0.78

/*

-0.78

-0.75

/*++

-0.72

<?

-0.70

 banish

-0.69

POSITIVE LOGITS

 soulign

1.31

 délib

1.30

 Rine

1.29

 véhic

1.28

Juf

1.22

 compréhen

1.21

 habile

1.20

 seksi

1.19

 Intere

1.18

 désol

1.16

Activations Density 0.093%

references to historical or academic figures and institutions

No Comments

No Known Activations