INDEX

Explanations

references to confidential information

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to confidentiality and sensitive information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Ì¶

-0.90

alis

-0.88

annis

-0.87

plex

-0.77

owitz

-0.75

 Mania

-0.73

imus

-0.73

ixels

-0.71

okemon

-0.70

akeru

-0.70

POSITIVE LOGITS

 confidential

1.17

 informants

1.03

 informant

1.03

idential

0.97

 correspondence

0.84

 documents

0.82

 confidentiality

0.82

 information

0.80

arial

0.80

 arrangements

0.79

Activations Density 0.017%

references to confidential information

terms and phrases related to confidentiality and sensitive information

No Comments

No Known Activations