INDEX

Explanations

instances where the word "you" is mentioned

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>

-1.82

-0.77

<?

-0.61

/**

-0.58

 defray

-0.57

 later

-0.56

 mobilize

-0.55

 enshr

-0.55

 turned

-0.54

 reunite

-0.54

POSITIVE LOGITS

 meis

1.13

 ananas

1.06

 incess

1.05

 kafe

1.05

 vinci

1.05

 maroc

1.03

 bandung

1.03

uhr

1.01

 baum

1.00

 saar

0.99

Activations Density 0.217%

instances where the word "you" is mentioned

No Comments

No Known Activations