INDEX

Explanations

phrases related to former positions or roles of individuals

oai_token-act-pair · gpt-3.5-turbo

phrases related to individuals who have held previous positions or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

uden

-0.87

Zup

-0.87

 shading

-0.80

oglu

-0.79

otle

-0.77

 dances

-0.73

kson

-0.71

utical

-0.70

 merits

-0.67

 largeDownload

-0.66

POSITIVE LOGITS

girlfriend

1.29

husband

1.18

member

1.06

Soviet

1.04

wife

1.02

may

1.01

president

1.01

employ

1.01

commun

0.99

marine

0.99

Activations Density 0.025%

phrases related to former positions or roles of individuals

phrases related to individuals who have held previous positions or relationships

No Comments

No Known Activations