INDEX

Explanations

references to the term "Americans"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Americans."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

fecture

-0.77

selection

-0.70

planet

-0.68

NB

-0.67

aster

-0.65

slot

-0.64

levant

-0.64

cffffcc

-0.64

Copy

-0.64

yz

-0.63

POSITIVE LOGITS

 Americans

0.93

Americans

0.82

 Indians

0.81

ICAN

0.78

 patri

0.77

icans

0.74

ervatives

0.74

alis

0.73

 colonists

0.73

 Allies

0.72

Activations Density 0.017%

references to the term "Americans"

mentions of the word "Americans."

No Comments

No Known Activations