INDEX

Explanations

references to similarity or equivalence in various contexts

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

Ĵ

-2.12

»

-1.99

Ŀ

-1.92

ĨĴ

-1.86

º

-1.84

ľĵ

-1.82

eva

-1.71

±

-1.67

Ľ

-1.65

son

-1.63

POSITIVE LOGITS

 amounts

1.86

 position

1.59

 positions

1.52

 between

1.49

ioned

1.47

 acting

1.46

 territories

1.45

 sized

1.43

rency

1.43

itance

1.42

Activations Density 0.014%

references to similarity or equivalence in various contexts

No Comments

No Known Activations