INDEX

Explanations

phrases indicating restrictions or limitations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CHA

-0.80

))))

-0.74

});

-0.73

imar

-0.72

asc

-0.69

mir

-0.67

enth

-0.66

MORE

-0.64

 syndrome

-0.64

ru

-0.63

POSITIVE LOGITS

 certain

0.94

 those

0.90

 essentials

0.83

 subsistence

0.79

 specific

0.79

 narrow

0.78

 emergencies

0.76

 nominal

0.74

 limited

0.74

 narrowly

0.73

Activations Density 0.182%

phrases indicating restrictions or limitations

No Comments

No Known Activations