INDEX

Explanations

phrases related to questionnaires

oai_token-act-pair · gpt-3.5-turbo

references to various types of questionnaires

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

practice

-0.75

current

-0.72

oli

-0.72

owners

-0.71

relative

-0.71

gets

-0.71

Ń

-0.68

Eye

-0.68

offs

-0.68

capital

-0.67

POSITIVE LOGITS

naires

1.40

naire

1.27

 questionnaire

1.22

issance

0.85

 Panzer

0.73

 Generator

0.73

BOX

0.67

BOX

0.67

mble

0.67

 shaped

0.67

Activations Density 0.018%

phrases related to questionnaires

references to various types of questionnaires

No Comments

No Known Activations