INDEX

Explanations

occurrences of the word 'the' followed by a significant word

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>

-3.64

-1.00

ⓧ

-0.94

/**

-0.89

<?

-0.88

<?

-0.72

/*

-0.70

/*!

-0.65

contentLoaded

-0.64

/***

-0.62

POSITIVE LOGITS

 bandung

1.24

 Minang

1.11

 affor

1.09

 maroc

1.09

 perpé

1.05

 seksi

1.05

 jawa

1.04

 gila

1.01

 lele

1.01

 Pekan

1.00

Activations Density 0.269%

occurrences of the word 'the' followed by a significant word

No Comments

No Known Activations