INDEX

Explanations

phrases related to getting away with something or receiving a relatively minor punishment

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Interstitial

-0.73

å¥³

-0.68

 circumference

-0.60

 succession

-0.57

çīĪ

-0.55

GMT

-0.55

 readiness

-0.55

 ambitions

-0.55

 Liang

-0.54

 capacities

-0.53

POSITIVE LOGITS

door

0.71

oned

0.66

yp

0.65

udeb

0.65

entary

0.63

/+

0.63

odor

0.62

ayne

0.62

retty

0.62

 easy

0.61

Activations Density 0.067%

phrases related to getting away with something or receiving a relatively minor punishment

No Comments

No Known Activations