INDEX

Explanations

phrases related to pedestrian infrastructure and safety

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 marrow

-0.89

outube

-0.73

xit

-0.73

anyahu

-0.72

temp

-0.71

mable

-0.70

cham

-0.69

 Centauri

-0.68

 Pharma

-0.67

zona

-0.64

POSITIVE LOGITS

 pedestrians

0.97

 pedestrian

0.80

jog

0.76

 patrol

0.75

 obstruct

0.74

 obstruction

0.74

 crossing

0.74

 walk

0.74

 crossings

0.72

walk

0.71

Activations Density 0.034%

phrases related to pedestrian infrastructure and safety

No Comments

No Known Activations