INDEX

Explanations

privacy-related terms

oai_token-act-pair · gpt-3.5-turbo

references to privacy and security

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

terday

-0.82

leys

-0.80

kell

-0.79

gling

-0.74

 Mead

-0.71

iggs

-0.71

uana

-0.71

naire

-0.69

 Kear

-0.67

gran

-0.65

POSITIVE LOGITS

Privacy

0.84

 privacy

0.83

 preferences

0.82

 preference

0.79

iframe

0.78

 actionGroup

0.73

 inbox

0.71

 email

0.70

 alert

0.70

policy

0.70

Activations Density 0.007%

privacy-related terms

references to privacy and security

No Comments

No Known Activations