INDEX

Explanations

words related to computer commands and online communication

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.43

<?

-1.07

-1.05

/**

-0.92

ⓧ

-0.87

/***

-0.84

<?

-0.83

///**

-0.78

/*!

-0.77

//{

-0.72

POSITIVE LOGITS

 stockholm

1.58

 wien

1.53

 lidl

1.46

 affor

1.42

 lamborghini

1.42

 ibiza

1.41

mef

1.40

 squa

1.38

 maneu

1.38

 dises

1.38

Activations Density 0.345%

words related to computer commands and online communication

No Comments

No Known Activations