INDEX

Explanations

names and personal details in texts

oai_token-act-pair · gpt-3.5-turbo

connections between names and personal information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

worms

-0.85

iculture

-0.75

rats

-0.73

Increases

-0.71

drm

-0.70

nw

-0.69

itized

-0.69

hawks

-0.68

ranged

-0.67

bub

-0.66

POSITIVE LOGITS

 surname

1.30

 nationality

1.26

 initials

1.20

 likeness

1.19

 password

1.16

 pronouns

1.09

 address

1.08

password

1.07

 suffix

1.05

 badge

1.02

Activations Density 0.185%

names and personal details in texts

connections between names and personal information

No Comments

No Known Activations