INDEX

Explanations

technical language related to system components and their configurations

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__mlp-sm_processed/2-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.2.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

eda

-1.71

arest

-1.54

Argued

-1.53

overnment

-1.52

ardo

-1.50

chanical

-1.50

ilities

-1.49

rong

-1.46

ERTY

-1.43

 indicated

-1.43

POSITIVE LOGITS

¿½

2.94

ĺ

2.77

ĨĴ

2.76

Īĺ

2.66

¾

2.66

Ĳ

2.66

·¸

2.64

Ļª

2.63

¥

2.52

§

2.50

Activations Density 1.928%

technical language related to system components and their configurations

No Comments

No Known Activations