INDEX

Explanations

the name "Dominic"

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

IFrame

Link

Negative Logits

 late

-1.92

 mercy

-1.67

 rapid

-1.59

her

-1.53

 daughters

-1.53

 newly

-1.53

 stolen

-1.51

Dad

-1.49

him

-1.48

 distant

-1.45

POSITIVE LOGITS

©

2.52

UAL

1.94

uelle

1.90

IBILITY

1.80

itud

1.77

uet

1.71

itude

1.69

issance

1.69

itto

1.69

ite

1.68

Activations Density 0.019%

the name "Dominic"

No Known Activations