INDEX

Explanations

detailed legal definitions or descriptions of specific technical terms or processes

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>

-1.69

omaterial

-0.71

/*

-0.70

/**

-0.68

 might

-0.65

}{||

-0.65

CodeAttribute

-0.63

 went

-0.63

can

-0.63

 could

-0.62

POSITIVE LOGITS

 accla

1.67

 maneu

1.65

 stockholm

1.53

 increa

1.51

 affor

1.48

 emphat

1.48

 wien

1.47

fta

1.46

 ?...

1.44

 lidl

1.43

Activations Density 0.139%

detailed legal definitions or descriptions of specific technical terms or processes

No Comments

No Known Activations