INDEX

Explanations

mentions of retirement and related terms

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.1.hook_resid_post

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

©

-2.02

ĨĴ

-1.99

ĥ½

-1.88

Īĺ

-1.86

ĵ

-1.85

Ĵ

-1.83

Ķ

-1.78

į

-1.74

ħ

-1.71

ī

-1.69

POSITIVE LOGITS

 junior

1.70

 retire

1.62

 senior

1.59

prising

1.59

icular

1.54

ftware

1.47

iating

1.45

ktop

1.43

 hobby

1.43

iator

1.40

Activations Density 0.169%

mentions of retirement and related terms

No Comments

No Known Activations