INDEX

Explanations

words related to productivity and efficiency

oai_token-act-pair · gpt-3.5-turbo

references to productivity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aida

-0.80

adr

-0.78

upon

-0.77

oho

-0.76

outed

-0.74

bole

-0.73

chip

-0.71

gran

-0.71

fee

-0.68

onne

-0.68

POSITIVE LOGITS

 productive

1.21

ãĥ¼ãĥĨ

0.97

productive

0.88

 productivity

0.85

folios

0.76

jo

0.75

 Downloads

0.75

tenance

0.73

ð

0.71

LF

0.71

Activations Density 0.005%

words related to productivity and efficiency

references to productivity

No Comments

No Known Activations