INDEX

Explanations

phrases related to comparisons or contrasts

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

uyomi

-0.77

dayName

-0.75

gee

-0.72

gger

-0.68

asma

-0.66

é¾įå¥ĳå£«

-0.64

rag

-0.63

boa

-0.62

merga

-0.60

jo

-0.59

POSITIVE LOGITS

us

0.93

 mankind

0.79

 humankind

0.77

 humanity

0.75

 civilisation

0.74

 spectrum

0.74

 eternity

0.74

 society

0.72

 Europe

0.72

 civilization

0.72

Activations Density 0.062%

phrases related to comparisons or contrasts

No Comments

No Known Activations