INDEX

Explanations

locations or settings related to adventure or exploration

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

CTV

-0.79

Americans

-0.78

elected

-0.77

payers

-0.74

 journalists

-0.72

 Catholics

-0.70

 taxpayers

-0.70

votes

-0.69

 Americans

-0.69

 Australians

-0.68

POSITIVE LOGITS

 labyrinth

1.43

 maze

1.41

 cavern

1.35

 dungeons

1.34

 depths

1.33

 caves

1.27

 dungeon

1.25

 abyss

1.24

 underworld

1.21

 jungle

1.21

Activations Density 0.609%

locations or settings related to adventure or exploration

No Comments

No Known Activations