INDEX

Explanations

terms related to questionnaires and surveys

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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ŀ

-0.69

bringing

-0.68

à

-0.66

ŃĶ

-0.65

Ath

-0.63

mob

-0.62

birds

-0.61

Ń

-0.60

ollar

-0.59

practice

-0.59

POSITIVE LOGITS

naires

1.08

 questionnaire

0.93

naire

0.92

ester

0.76

asures

0.71

isition

0.69

 checklist

0.67

issance

0.66

OPLE

0.66

raine

0.66

Activations Density 0.013%

terms related to questionnaires and surveys

references to various types of questionnaires

No Comments

No Known Activations