INDEX

Explanations

phrases related to sources or individuals who wish to remain anonymous

oai_token-act-pair · gpt-3.5-turbo

references to anonymity and the conditions surrounding it

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

joice

-0.79

gra

-0.69

 Rally

-0.62

 delinqu

-0.61

setting

-0.60

 fundamentals

-0.59

 Tend

-0.58

 joints

-0.57

killing

-0.57

tumblr

-0.57

POSITIVE LOGITS

 anonymity

1.20

 surn

1.07

 emailed

0.89

 confidentiality

0.88

 UNCLASSIFIED

0.84

 anonymous

0.83

 pseudonym

0.83

 anonymously

0.80

 disclosed

0.80

 unnamed

0.80

Activations Density 0.782%

phrases related to sources or individuals who wish to remain anonymous

references to anonymity and the conditions surrounding it

No Comments

No Known Activations