INDEX

Explanations

references to places where people live, specifically focusing on "homes."

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

ı

-2.62

Ŀ

-2.61

¯

-2.55

↵

-2.55

↵

-2.55

↵

-2.55

č↵

-2.55

↵

-2.55

<|outofrange|>

-2.55

POSITIVE LOGITS

oque

2.20

creen

2.14

chool

2.00

pun

1.99

heet

1.83

weet

1.77

cript

1.71

 pose

1.69

heets

1.64

 offence

1.63

Activations Density 0.082%

references to places where people live, specifically focusing on "homes."

No Comments

No Known Activations