INDEX

Explanations

references to the United States

oai_token-act-pair · gpt-3.5-turbo

references to the United States

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

 newcom

-0.78

ajo

-0.76

 streng

-0.70

 exting

-0.68

 dazz

-0.66

 enthusi

-0.65

ãĤ´

-0.65

 mosqu

-0.64

 tremend

-0.63

 mathemat

-0.62

POSITIVE LOGITS

 States

1.84

States

1.37

 STATES

1.35

 Nations

1.35

 Kingdom

1.23

 State

0.97

 Methodist

0.96

 states

0.91

 Nation

0.91

 Confederate

0.88

Activations Density 0.027%

references to the United States

references to the United States

No Comments

No Known Activations