INDEX

Explanations

phrases conveying a lack of concern or interest

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

hement

-0.85

ori

-0.84

DragonMagazine

-0.84

NAS

-0.82

zynski

-0.81

igmatic

-0.78

icol

-0.75

ãĥ¯ãĥ³

-0.74

oun

-0.74

 Cosponsors

-0.73

POSITIVE LOGITS

 preserving

1.07

 whether

0.99

 aesthetics

0.97

 protecting

0.89

 specifics

0.87

 accuracy

0.86

 hygiene

0.86

 maximizing

0.85

 finances

0.84

 details

0.84

Activations Density 0.186%

phrases conveying a lack of concern or interest

No Comments

No Known Activations