INDEX

Explanations

words related to privacy or data protection

oai_token-act-pair · gpt-3.5-turbo

terms related to privacy

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xual

-0.82

kell

-0.72

cki

-0.70

annis

-0.67

mount

-0.63

ithing

-0.63

ensen

-0.63

×Ļ×

-0.63

iatus

-0.61

flat

-0.61

POSITIVE LOGITS

 privacy

0.89

 Rights

0.86

 rights

0.86

 protections

0.84

 Liberties

0.78

 safeguards

0.75

 liberties

0.75

 Preferences

0.74

rights

0.74

policy

0.73

Activations Density 0.021%

words related to privacy or data protection

terms related to privacy

No Comments

No Known Activations