INDEX

Explanations

country names

oai_token-act-pair · gpt-3.5-turbo

references to specific countries and geopolitical issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

lance

-0.77

lesi

-0.67

ppings

-0.66

mons

-0.66

DonaldTrump

-0.65

laws

-0.64

ateurs

-0.64

netflix

-0.64

BILITIES

-0.62

cd

-0.62

POSITIVE LOGITS

 ratio

1.37

 Ratio

1.28

 hybrids

1.24

 hybrid

1.23

 combo

1.23

 dich

1.20

 relationship

1.19

 partnership

1.17

 rivalry

1.17

 ratios

1.16

Activations Density 0.201%

country names

references to specific countries and geopolitical issues

No Comments

No Known Activations