INDEX

Explanations

references to famous restaurants or culinary establishments

oai_token-act-pair · gpt-3.5-turbo

names of people, places, or organizations

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

behind

-0.88

requ

-0.81

rael

-0.80

udeb

-0.79

ngth

-0.75

bsite

-0.70

lance

-0.70

currently

-0.68

olves

-0.68

undo

-0.68

POSITIVE LOGITS

 Gate

0.95

 Prize

0.90

 Valley

0.89

 Square

0.87

 Circle

0.83

 Grande

0.82

 Cruise

0.82

 Canyon

0.77

 Pavilion

0.77

 Heights

0.76

Activations Density 0.171%

references to famous restaurants or culinary establishments

names of people, places, or organizations

No Comments

No Known Activations