INDEX

Explanations

terms related to phosphorus and its compounds

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

 tendency

-1.58

 defects

-1.58

hip

-1.51

rfloor

-1.49

 deleterious

-1.49

 defect

-1.48

ward

-1.46

unting

-1.46

rely

-1.44

 propensity

-1.40

POSITIVE LOGITS

electric

1.97

assic

1.76

inux

1.58

"}](#

1.54

ony

1.54

optic

1.49

asses

1.46

oon

1.45

inski

1.45

erg

1.43

Activations Density 3.081%

terms related to phosphorus and its compounds

No Comments

No Known Activations