INDEX

Explanations

directives related to establishing outcomes and making determinations in various contexts

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

ĥ½

-3.87

¸

-3.73

ŀ

-3.70

¬

-3.67

ĭ

-3.66

Ľ

-3.64

ľ

-3.62

¯

-3.59

ĳ

-3.51

Ħ

-3.44

POSITIVE LOGITS

igan

1.66

Aid

1.65

 scrambled

1.57

etable

1.47

 Corps

1.46

 corps

1.44

 adulthood

1.44

 combat

1.43

amed

1.41

 brains

1.40

Activations Density 0.006%

directives related to establishing outcomes and making determinations in various contexts

No Comments

No Known Activations