INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize significant or prominent subjects within a context

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

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

SPONSORED

-0.91

pps

-0.82

leck

-0.74

erson

-0.73

assium

-0.68

enced

-0.68

thumbnails

-0.68

ï¸ı

-0.66

pired

-0.66

NK

-0.66

POSITIVE LOGITS

 bandwagon

0.95

rug

0.94

 mantle

0.87

 carpet

0.83

 sofa

0.78

 treadmill

0.78

 dime

0.76

 notion

0.75

 generosity

0.75

 ledge

0.74

Activations Density 0.383%

proper nouns

phrases that emphasize significant or prominent subjects within a context

No Comments

No Known Activations