INDEX

Explanations

sentences related to a process or change over time

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>

-2.65

ⓧ

-0.99

<?

-0.85

/*

-0.83

/***

-0.73

-0.72

/**

-0.72

///**

-0.71

<?

-0.68

POSITIVE LOGITS

 affor

1.70

 maneu

1.67

 impra

1.56

 accla

1.53

 reluct

1.50

 resear

1.49

 disagre

1.46

Juf

1.45

 emphat

1.45

 increa

1.44

Activations Density 0.410%

sentences related to a process or change over time

No Comments

No Known Activations