INDEX

Explanations

phrases or words related to admissions of guilt or ownership

oai_token-act-pair · gpt-3.5-turbo

instances of the word "admit" and its variations, indicating admissions of guilt or truthfulness

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

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

 ILCS

-0.82

rior

-0.71

osi

-0.70

ighth

-0.68

acements

-0.67

atility

-0.66

ãĤ¡

-0.65

asus

-0.64

rouse

-0.63

adesh

-0.63

POSITIVE LOGITS

 wrongdoing

1.07

 defeat

1.01

 guilt

0.99

 responsibility

0.78

 ignorance

0.77

 admitting

0.77

 mistakes

0.77

 fault

0.76

 culp

0.74

 admit

0.74

Activations Density 0.057%

phrases or words related to admissions of guilt or ownership

instances of the word "admit" and its variations, indicating admissions of guilt or truthfulness

No Comments

No Known Activations