INDEX

Explanations

dates and events in a structured format

oai_token-act-pair · gpt-3.5-turbo

references to prominent individuals or public figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Â¢

-0.87

PHI

-0.87

STEM

-0.81

Seattle

-0.80

Kids

-0.80

ADA

-0.80

Â®,

-0.78

Madison

-0.76

Indiana

-0.76

NYC

-0.76

POSITIVE LOGITS

zbollah

1.31

 Syri

1.16

 Rouhani

1.13

 Islamists

1.12

 Erdogan

1.12

 Gaddafi

1.10

 Hollande

1.10

 defiant

1.09

 Islamist

1.08

 nationalist

1.08

Activations Density 0.883%

dates and events in a structured format

references to prominent individuals or public figures

No Comments

No Known Activations