INDEX

Explanations

terms related to promoting or increasing awareness on various topics

oai_token-act-pair · gpt-3.5-turbo

phrases related to raising awareness on various social issues

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

ãĥĥãĥī

-0.72

hetti

-0.71

compan

-0.67

rett

-0.66

Textures

-0.63

coni

-0.63

scenes

-0.61

anova

-0.61

rou

-0.60

 Arkham

-0.59

POSITIVE LOGITS

 awareness

1.22

awareness

1.00

 Awareness

0.98

ibility

0.80

fulness

0.78

irtual

0.76

ledged

0.74

?????

0.73

orship

0.72

uggest

0.72

Activations Density 0.024%

terms related to promoting or increasing awareness on various topics

phrases related to raising awareness on various social issues

No Comments

No Known Activations