INDEX

Explanations

references to noble titles and royalty

oai_token-act-pair · gpt-3.5-turbo

titles or ranks related to nobility and royalty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

crew

-0.76

ucha

-0.74

consumer

-0.73

cms

-0.71

aval

-0.71

inem

-0.70

aukee

-0.70

 crate

-0.69

 fracture

-0.69

aping

-0.69

POSITIVE LOGITS

 Theodore

1.06

 Philip

1.04

 John

1.01

 Joseph

1.00

 Pierre

1.00

 Gerald

1.00

 Francis

0.99

 William

0.99

 Richard

0.98

 Ferdinand

0.98

Activations Density 0.170%

references to noble titles and royalty

titles or ranks related to nobility and royalty

No Comments

No Known Activations