INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/2-res-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_resid_post

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

atile

-1.54

othetical

-1.51

¨

-1.50

 unity

-1.49

ubuntu

-1.43

||

-1.42

arly

-1.39

itage

-1.38

*=

-1.35

 analyst

-1.33

POSITIVE LOGITS

iley

1.70

 chase

1.67

tees

1.49

 route

1.47

pee

1.44

shore

1.43

 tandem

1.41

ientes

1.39

ITC

1.38

iente

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.