INDEX

Explanations

terms related to privacy and security concerns

oai_token-act-pair · gpt-3.5-turbo

vocabulary related to privacy concerns and data security issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

assad

-0.82

ascus

-0.79

 McMahon

-0.75

ciation

-0.74

ugi

-0.73

 Variant

-0.71

 welding

-0.69

agic

-0.68

wagon

-0.68

 Bowen

-0.68

POSITIVE LOGITS

 privacy

2.03

Privacy

1.99

 Privacy

1.90

 encryption

1.62

 anonym

1.48

 encrypt

1.47

 encrypted

1.43

 Surveillance

1.42

 surveillance

1.40

 cybersecurity

1.33

Activations Density 0.559%

terms related to privacy and security concerns

vocabulary related to privacy concerns and data security issues

No Comments

No Known Activations