INDEX

Explanations

sequences of hyphens and numbers

oai_token-act-pair · gpt-3.5-turbo

negative indicators associated with health and risk factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ulhu

-0.83

Wiz

-0.81

 Borders

-0.79

 Mama

-0.77

ãģ®å®

-0.77

 Bloody

-0.75

 Fiesta

-0.74

 Bullets

-0.73

 Lady

-0.72

 Rivals

-0.72

POSITIVE LOGITS

mediated

1.28

derived

1.22

containing

1.20

shaped

1.19

biased

1.17

induced

1.17

dimensional

1.16

specific

1.15

treated

1.12

processing

1.11

Activations Density 0.168%

sequences of hyphens and numbers

negative indicators associated with health and risk factors

No Comments

No Known Activations