INDEX

Explanations

elements of documentation or commentary in code

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

acity

-1.50

ex

-1.35

ently

-1.33

 whose

-1.31

 obstruction

-1.31

 contribut

-1.30

 command

-1.26

lest

-1.25

 opposing

-1.25

emy

-1.23

POSITIVE LOGITS

ģ

1.85

°

1.69

ĻĤ

1.67

 Pradesh

1.66

«

1.58

¶

1.47

ian

1.46

auf

1.46

anne

1.42

izumab

1.41

Activations Density 0.129%

elements of documentation or commentary in code

No Comments

No Known Activations