INDEX

Explanations

evaluations or feedback related to games

oai_token-act-pair · gpt-3.5-turbo

expressions of dissatisfaction or unfairness in games

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Feinstein

-0.83

 Qiao

-0.82

 Leban

-0.79

 Bulgar

-0.79

qqa

-0.78

 Berkshire

-0.78

anson

-0.77

 lashes

-0.76

 Bris

-0.75

 Raqqa

-0.75

POSITIVE LOGITS

 Game

2.25

Game

2.24

game

2.07

 GAME

2.05

 game

1.95

GAME

1.83

games

1.80

 games

1.76

 Games

1.74

Games

1.72

Activations Density 0.237%

evaluations or feedback related to games

expressions of dissatisfaction or unfairness in games

No Comments

No Known Activations