INDEX

Explanations

references to computer code execution or processing commands

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

Not in Any Lists

No Comments

Negative Logits

Īĺ

-2.97

ĨĴ

-2.86

ľĵ

-2.76

ĻĤ

-2.43

Ļª

-2.40

ĸ´

-2.39

Ł

-2.33

Ĥ¬

-2.33

²

-2.27

º

-2.26

POSITIVE LOGITS

recht

2.25

ware

1.96

etable

1.87

ruptcy

1.85

aret

1.85

ETS

1.85

etts

1.82

rooms

1.78

verts

1.76

laws

1.74

Activations Density 0.116%

references to computer code execution or processing commands

No Comments

No Known Activations