INDEX

Explanations

proper nouns related to a specific location - "Napoli"

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "Nap" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

DonaldTrump

-0.76

 Gemini

-0.76

âĢ¢âĢ¢

-0.71

 Carbuncle

-0.70

UCT

-0.64

×Ļ×

-0.64

 Drift

-0.63

RECT

-0.63

--------------------------------

-0.62

BI

-0.62

POSITIVE LOGITS

oleon

1.66

alm

1.38

olit

1.34

olitan

1.27

erville

1.19

olean

1.18

oli

1.10

ole

0.92

kins

0.91

olini

0.91

Activations Density 0.042%

proper nouns related to a specific location - "Napoli"

the presence of the word "Nap" in various contexts

No Comments

No Known Activations