INDEX

Explanations

names of scholars, writers, and public figures

oai_token-act-pair · gpt-3.5-turbo

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

 srfAttach

-0.75

window

-0.74

twitch

-0.73

Plex

-0.73

 actionGroup

-0.72

venge

-0.72

Emergency

-0.69

FTWARE

-0.67

crew

-0.65

 Tradable

-0.65

POSITIVE LOGITS

 argues

1.59

 writes

1.40

 cites

1.39

 summarizes

1.38

 discusses

1.35

 concludes

1.34

 contends

1.33

 argued

1.31

 observes

1.30

 asserts

1.30

Activations Density 0.367%

names of scholars, writers, and public figures

No Comments

No Known Activations