INDEX

Explanations

references to anonymity or anonymous entities in text

oai_token-act-pair · gpt-3.5-turbo

references to anonymity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

NEY

-0.87

Fan

-0.77

forces

-0.77

neys

-0.76

Eng

-0.73

bourg

-0.73

enegger

-0.72

yg

-0.72

FK

-0.71

united

-0.71

POSITIVE LOGITS

 anonymous

1.12

 anonymity

1.06

onym

0.93

onymous

0.89

 bystand

0.88

 informant

0.87

 anonymously

0.82

otine

0.82

 anonym

0.80

 retirement

0.78

Activations Density 0.014%

references to anonymity or anonymous entities in text

references to anonymity

No Comments

No Known Activations