INDEX

Explanations

descriptions of new elements, features, or updates in a game

oai_token-act-pair · gpt-3.5-turbo

phrases relating to new game features and content updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

govtrack

-0.86

Bloomberg

-0.83

Wikipedia

-0.82

inventoryQuantity

-0.82

rational

-0.79

PLIED

-0.77

Ô

-0.77

wikipedia

-0.76

onday

-0.75

typically

-0.73

POSITIVE LOGITS

 playable

1.52

 gameplay

1.46

DLC

1.34

 multiplayer

1.31

 storyline

1.29

 costumes

1.25

 dungeons

1.25

 bonus

1.24

 unlock

1.22

 quests

1.19

Activations Density 0.406%

descriptions of new elements, features, or updates in a game

phrases relating to new game features and content updates

No Comments

No Known Activations