INDEX

Explanations

words related to authoritarianism and totalitarianism

oai_token-act-pair · gpt-3.5-turbo

terms related to authoritarianism and totalitarianism

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

ovember

-0.89

 Tire

-0.86

 Myster

-0.82

fair

-0.81

ttp

-0.80

************

-0.79

ale

-0.77

llo

-0.75

cloth

-0.74

igating

-0.74

POSITIVE LOGITS

 regimes

1.29

 dictatorship

1.16

 dictator

1.15

 dictators

1.11

 totalitarian

1.06

 authoritarian

1.04

 regime

0.99

 ideologies

0.98

 tendencies

0.96

 repressive

0.95

Activations Density 0.029%

words related to authoritarianism and totalitarianism

terms related to authoritarianism and totalitarianism

No Comments

No Known Activations