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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

usalem

-1.83

à±ģ

-1.81

rial

-1.74

selector

-1.62

iza

-1.58

abad

-1.57

iginally

-1.55

liament

-1.53

veis

-1.51

aurant

-1.46

POSITIVE LOGITS

lessness

1.63

¬

1.47

ĸ

1.45

ĥ½

1.44

 where

1.43

 blown

1.42

 struggles

1.39

where

1.36

 vista

1.33

RESULTS

1.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.