INDEX

Explanations

mentions of terrorist groups such as Al Qaeda, in particular, the name "Al" followed by a high activation value

oai_token-act-pair · gpt-3.5-turbo

references to "Al Qaeda."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ãĥ¼ãĥĨãĤ£

-0.93

 Vaugh

-0.83

 Tycoon

-0.78

manship

-0.76

 Cricket

-0.75

å£

-0.73

 Mechdragon

-0.72

 Lovecraft

-0.71

lihood

-0.70

 Seah

-0.70

POSITIVE LOGITS

manac

1.14

 Jazeera

1.13

gebra

1.11

addin

1.07

ameda

1.00

umni

0.98

 Qaeda

0.97

iyah

0.96

oha

0.96

una

0.94

Activations Density 0.020%

mentions of terrorist groups such as Al Qaeda, in particular, the name "Al" followed by a high activation value

references to "Al Qaeda."

No Comments

No Known Activations