INDEX

Explanations

words related to privacy and data protection

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.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

-0.71

kell

-0.71

cki

-0.66

Production

-0.66

mount

-0.64

stad

-0.64

enson

-0.64

ithing

-0.64

nant

-0.64

lift

-0.63

POSITIVE LOGITS

 protections

1.00

 rights

0.99

 Rights

0.93

 safeguards

0.88

 privacy

0.87

rights

0.85

 liberties

0.83

policy

0.80

 Liberties

0.80

 freedoms

0.79

Activations Density 0.024%

words related to privacy and data protection

No Comments

No Known Activations