INDEX

Explanations

phrases or words related to political dynasties

oai_token-act-pair · gpt-3.5-turbo

references to dynasties and the concept of succession

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

anchester

-0.82

ynthesis

-0.80

ãĥ¤

-0.78

horn

-0.77

erial

-0.72

isconsin

-0.72

lando

-0.72

stadt

-0.72

erville

-0.72

matter

-0.72

POSITIVE LOGITS

dyn

1.17

 dynasty

1.06

interstitial

0.98

doms

0.86

 monarchy

0.80

 patriarch

0.77

DOM

0.76

 clans

0.75

 empires

0.75

 clan

0.75

Activations Density 0.021%

phrases or words related to political dynasties

references to dynasties and the concept of succession

No Comments

No Known Activations