INDEX

Explanations

terms and concepts related to magnetic fields

oai_token-act-pair · gpt-3.5-turbo

references to magnetic concepts and phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

-0.84

ership

-0.81

 Columb

-0.75

soDeliveryDate

-0.73

FORE

-0.71

ELL

-0.71

EY

-0.71

akings

-0.71

 PsyNet

-0.70

 Pric

-0.70

POSITIVE LOGITS

netic

1.09

 resonance

1.07

 magnetic

1.00

 compass

0.96

 magnets

0.92

 coils

0.90

 monop

0.87

 coil

0.87

 susceptibility

0.87

 jerk

0.86

Activations Density 0.019%

terms and concepts related to magnetic fields

references to magnetic concepts and phenomena

No Comments

No Known Activations