INDEX

Explanations

phrases containing the name "Jo"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Jo"

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

 IMAGES

-0.72

flies

-0.70

 interests

-0.66

IFIED

-0.65

 Fired

-0.65

 amplification

-0.64

ashtra

-0.63

oÄŁ

-0.63

enegger

-0.63

 containment

-0.63

POSITIVE LOGITS

aquin

1.30

Jo

1.25

anne

1.09

jo

1.08

ining

1.03

ppa

1.03

zeb

1.02

Anne

1.00

zy

0.99

areth

0.98

Activations Density 0.025%

phrases containing the name "Jo"

mentions of the name "Jo"

No Comments

No Known Activations