INDEX

Explanations

terms related to nutrition and its components

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/2-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.2.hook_resid_post

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cause

-2.12

haviour

-1.78

havior

-1.67

watson

-1.63

legate

-1.49

illance

-1.46

plit

-1.44

ances

-1.43

andin

-1.42

POSITIVE LOGITS

hers

2.21

ters

1.99

iated

1.85

iful

1.84

ricular

1.82

aneous

1.80

hentication

1.79

hentic

1.74

iate

1.73

ochond

1.68

Activations Density 0.219%

terms related to nutrition and its components

No Comments

No Known Activations