INDEX

Explanations

business-related terms, including company names and product information

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>

-2.74

ⓧ

-0.96

/***

-0.79

///**

-0.78

/**

-0.70

<tfoot>

-0.69

Kontrola

-0.67

addPreferredGap

-0.64

PerformLayout

-0.63

//});

-0.62

POSITIVE LOGITS

 increa

1.72

 impra

1.69

 disagre

1.66

 affor

1.65

 maneu

1.61

 thut

1.57

 swarovski

1.57

 unlaw

1.56

 reluct

1.55

 stockholm

1.54

Activations Density 0.488%

business-related terms, including company names and product information

No Comments

No Known Activations