INDEX

Explanations

nationalities and citizenship statuses

oai_token-act-pair · gpt-3.5-turbo

references to various nationalities and citizenship statuses

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

Nut

-0.70

 Tactics

-0.66

 Siren

-0.65

Measure

-0.63

 Suggest

-0.63

ragon

-0.62

 Frenzy

-0.62

Tools

-0.61

EMS

-0.60

 feedback

-0.60

POSITIVE LOGITS

 abroad

1.11

 visas

1.09

 visa

1.05

 residing

0.97

 deported

0.97

 passports

0.93

 overseas

0.92

 consulate

0.89

 passport

0.88

 nationals

0.87

Activations Density 0.112%

nationalities and citizenship statuses

references to various nationalities and citizenship statuses

No Comments

No Known Activations