INDEX

Explanations

mentions of drunkenness or related behavior in police reports

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.07

లాలు

-0.76

/**

-0.66

//

-0.66

public

-0.65

class

-0.65

 بتاريخ

-0.64

/**

-0.63

/*

-0.63

HasAnnotation

-0.62

POSITIVE LOGITS

 drunk

2.08

 affor

1.94

 impra

1.93

 Drunk

1.87

 increa

1.86

drunk

1.82

 stockholm

1.80

 drunken

1.80

 sappi

1.77

aen

1.75

Activations Density 0.127%

mentions of drunkenness or related behavior in police reports

No Comments

No Known Activations