INDEX

Explanations

phrases related to physical descriptions or conditions, especially ones related to clothing or appearance

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

Reviewer

-0.75

 Hasan

-0.64

rers

-0.62

vation

-0.61

 indirectly

-0.59

ãĥ¼ãĥĨ

-0.58

 heads

-0.58

 Hamm

-0.56

 Scotia

-0.55

 exit

-0.54

POSITIVE LOGITS

poke

1.42

iege

1.33

erker

1.24

pect

1.13

earchers

1.01

peak

0.95

aved

0.95

oin

0.94

erk

0.93

hirt

0.90

Activations Density 0.033%

phrases related to physical descriptions or conditions, especially ones related to clothing or appearance

No Comments

No Known Activations