INDEX

Explanations

links or descriptions related to accessing full content, such as images or articles

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.08

<>

-0.77

///**

-0.74

/***

-0.73

/*!

-0.70

//---

-0.65

/**

-0.62

<?

-0.61

 introduce

-0.60

//--

-0.60

POSITIVE LOGITS

 stockholm

1.42

 bandung

1.40

 Minang

1.39

 maneu

1.36

 affor

1.36

 frankfurt

1.30

 unlaw

1.30

 venuto

1.29

Juf

1.29

 napoli

1.27

Activations Density 0.116%

links or descriptions related to accessing full content, such as images or articles

No Comments

No Known Activations