INDEX

Explanations

questions or scenarios requiring an opinion or decision

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

Negative Logits

ⓧ

-1.01

-0.99

/**

-0.95

<?

-0.93

/***

-0.87

/*

-0.79

<bos>

-0.78

<?

-0.78

/*!

-0.74

#![

-0.71

POSITIVE LOGITS

 maneu

1.62

 affor

1.51

 reluct

1.48

 accla

1.46

 stockholm

1.44

 increa

1.41

 impra

1.39

 shenan

1.38

 fortn

1.38

 eiffel

1.38

Activations Density 0.245%

questions or scenarios requiring an opinion or decision

No Known Activations