INDEX

Explanations

words related to confessions or admissions of guilt or wrongdoing

oai_token-act-pair · gpt-3.5-turbo

expressions of acknowledgment or admission of wrongdoing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

asus

-0.84

 ILCS

-0.76

assic

-0.74

rouse

-0.74

osi

-0.72

phabet

-0.72

DragonMagazine

-0.71

rior

-0.71

ighth

-0.70

prev

-0.70

POSITIVE LOGITS

 defeat

1.20

 wrongdoing

1.16

 guilt

1.08

 mistakes

1.00

 ignorance

0.93

 fault

0.92

 responsibility

0.90

 shortcomings

0.88

 admitting

0.87

 failings

0.84

Activations Density 0.051%

words related to confessions or admissions of guilt or wrongdoing

expressions of acknowledgment or admission of wrongdoing

No Comments

No Known Activations