INDEX

Explanations

technical information related to software updates, warranties, and product descriptions

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>

-3.48

ⓧ

-1.00

-0.90

/**

-0.89

<?

-0.87

/*

-0.84

-0.69

、

-0.68

 continue

-0.67

Referències

-0.65

POSITIVE LOGITS

 Minang

1.45

 lele

1.44

 véhic

1.40

 dises

1.38

 milano

1.37

 bandung

1.36

Juf

1.36

 inev

1.35

 lidl

1.34

 accla

1.34

Activations Density 1.126%

technical information related to software updates, warranties, and product descriptions

No Comments

No Known Activations