INDEX

Explanations

leadership positions or titles within organizations

oai_token-act-pair · gpt-3.5-turbo

mentions of leadership positions or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 IMAGES

-0.84

 suscept

-0.71

 tolerance

-0.66

Sharp

-0.63

 Apocalypse

-0.62

 firsthand

-0.60

 Ultron

-0.60

 uninsured

-0.59

 susceptibility

-0.59

 ransomware

-0.59

POSITIVE LOGITS

person

1.25

woman

1.24

chair

1.16

manship

1.16

mans

1.14

lift

1.11

 chair

1.10

holder

0.99

men

0.99

chairs

0.99

Activations Density 0.017%

leadership positions or titles within organizations

mentions of leadership positions or titles

No Comments

No Known Activations