INDEX

Explanations

declarations in programming code

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

Ľ

-2.24

Ĳ

-2.20

ĭ

-2.09

ı

-2.05

³

-2.05

ī

-2.04

¥

-2.00

²

-1.96

ĳ

-1.93

Īĺ

-1.92

POSITIVE LOGITS

 caption

1.61

factory

1.46

actors

1.43

amycin

1.42

 structures

1.41

 suppressor

1.39

puted

1.37

arial

1.37

ventional

1.36

pile

1.33

Activations Density 0.651%

declarations in programming code

No Comments

No Known Activations