INDEX

Explanations

references to seeing beyond the surface or understanding the deeper aspects of a subject

oai_token-act-pair · gpt-3.5-turbo

references to inner workings or internal aspects of systems and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

eday

-0.86

atoes

-0.84

orthy

-0.82

enegger

-0.78

HAHAHAHA

-0.76

enance

-0.75

essors

-0.75

SHIP

-0.74

HCR

-0.72

ILLE

-0.72

POSITIVE LOGITS

 workings

1.27

most

1.18

 sanct

0.89

 combustion

0.87

ranean

0.78

 circle

0.76

 turmoil

0.72

 circumference

0.71

wear

0.71

 thigh

0.70

Activations Density 0.014%

references to seeing beyond the surface or understanding the deeper aspects of a subject

references to inner workings or internal aspects of systems and experiences

No Comments

No Known Activations