INDEX

Explanations

technical or coding terminology related to programming, state management, and data structures

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

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

 scoop

-1.60

ovo

-1.50

 cookies

-1.43

 pitcher

-1.39

maid

-1.38

 glasses

-1.38

 cassette

-1.29

 flav

-1.26

 MgCl

-1.25

acious

-1.25

POSITIVE LOGITS

 deaths

1.56

ales

1.51

onse

1.51

lands

1.50

ACP

1.47

own

1.38

Īĺ

1.38

ir

1.37

onica

1.36

umni

1.35

Activations Density 4.086%

technical or coding terminology related to programming, state management, and data structures

No Comments

No Known Activations