INDEX

Explanations

terms related to cyber security and associated threats

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.0.hook_mlp_out

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

į

-2.12

ĨĴ

-2.03

Ľ

-1.87

Ļª

-1.86

ĸ´

-1.83

Ļ

-1.70

 present

-1.66

·¸

-1.62

ľ

-1.62

½

-1.61

POSITIVE LOGITS

crime

1.74

atÃ³

1.67

punk

1.66

notes

1.65

prints

1.59

 urges

1.59

bour

1.57

ips

1.54

 tracts

1.54

waves

1.53

Activations Density 1.594%

terms related to cyber security and associated threats

No Comments

No Known Activations