INDEX

Explanations

references to article sections/lists

oai_token-act-pair · gpt-3.5-turbo

highlighted notes or important points in a text

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

 whoever

-0.60

Brien

-0.59

 nurt

-0.57

existent

-0.57

Whoever

-0.56

adle

-0.55

 conscientious

-0.55

 seizing

-0.55

Luckily

-0.55

 confid

-0.54

POSITIVE LOGITS

PDF

1.01

FAQ

1.00

 screenshots

0.94

 Downloads

0.93

pdf

0.92

 Transcript

0.91

 annotations

0.91

 descriptions

0.89

 downloadable

0.88

 Contents

0.88

Activations Density 0.423%

references to article sections/lists

highlighted notes or important points in a text

No Comments

No Known Activations