INDEX

Explanations

mentions of the name "Osama bin Laden."

oai_token-act-pair · gpt-3.5-turbo

mentions of Osama bin Laden

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

drawn

-0.75

eries

-0.74

ships

-0.74

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.70

hire

-0.68

flies

-0.67

haw

-0.66

WD

-0.66

hips

-0.65

place

-0.65

POSITIVE LOGITS

bin

1.21

Bin

1.10

 Osama

0.99

 Hussein

0.97

 Laden

0.88

 rall

0.86

 Hassan

0.85

ibn

0.82

 Sharif

0.80

abad

0.80

Activations Density 0.003%

mentions of the name "Osama bin Laden."

mentions of Osama bin Laden

No Comments

No Known Activations