INDEX

Explanations

proper nouns of places or organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns, especially names of places and entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wagen

-0.77

ĸļ

-0.75

 Canaver

-0.74

 Horus

-0.71

Material

-0.70

lihood

-0.66

ynthesis

-0.64

 Prol

-0.64

 Osiris

-0.64

inventoryQuantity

-0.64

POSITIVE LOGITS

 citiz

0.99

apolis

0.91

ians

0.90

 municipality

0.89

 City

0.86

landers

0.86

outheastern

0.85

 County

0.85

 residents

0.83

 municipalities

0.82

Activations Density 0.314%

proper nouns of places or organizations

proper nouns, especially names of places and entities

No Comments

No Known Activations