INDEX

Explanations

proper nouns related to locations

oai_token-act-pair · gpt-3.5-turbo

references to the location "Kashmir."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Antiqu

-0.85

 Sabb

-0.69

 Administ

-0.68

 Sting

-0.66

 Stephenson

-0.64

 Pompe

-0.64

 fallout

-0.63

 Alger

-0.63

 Chad

-0.63

ourn

-0.61

POSITIVE LOGITS

ku

3.83

zu

2.82

eka

2.04

shi

1.81

ju

1.40

kai

1.24

iku

1.21

tu

1.17

zhou

1.15

ribune

1.11

Activations Density 0.019%

proper nouns related to locations

references to the location "Kashmir."

No Comments

No Known Activations