INDEX

Explanations

terms related to secret societies and conspiracy theories

oai_token-act-pair · gpt-3.5-turbo

terms and concepts related to the occult and secret societies

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

 Kers

-0.78

abs

-0.75

cknowled

-0.75

HF

-0.74

worthiness

-0.73

BILITY

-0.72

 Ender

-0.70

player

-0.68

 Cheong

-0.66

 Obst

-0.66

POSITIVE LOGITS

 symbolism

0.99

 ritual

0.95

 rituals

0.93

 Illuminati

0.90

 indoctr

0.86

 Ritual

0.79

 dictatorship

0.78

 occult

0.77

anism

0.77

 hypnot

0.76

Activations Density 0.104%

terms related to secret societies and conspiracy theories

terms and concepts related to the occult and secret societies

No Comments

No Known Activations