INDEX

Explanations

words related to actions or descriptions of uncovering or revealing unknown or hidden information

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

acious

-0.65

 forgiven

-0.63

 vectors

-0.62

 selves

-0.61

selves

-0.60

 differe

-0.60

 Shed

-0.59

 Egyptians

-0.58

 gritty

-0.58

 Brah

-0.57

POSITIVE LOGITS

ffee

1.50

verage

1.34

xon

1.33

operative

1.22

operation

1.20

herent

1.18

aching

1.15

ff

1.15

pper

1.12

venant

1.11

Activations Density 0.024%

words related to actions or descriptions of uncovering or revealing unknown or hidden information

No Comments

No Known Activations