INDEX

Explanations

phrases related to a person or thing going back to a previous state or place

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of returning

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

arta

-0.84

ital

-0.71

Tube

-0.68

chn

-0.68

tec

-0.68

ean

-0.67

nih

-0.66

ismo

-0.63

oshop

-0.62

conom

-0.62

POSITIVE LOGITS

 returning

3.51

 Returning

2.62

 return

1.99

 returned

1.85

 returns

1.81

 Return

1.78

 departing

1.76

return

1.72

Return

1.70

 exiting

1.61

Activations Density 0.008%

phrases related to a person or thing going back to a previous state or place

phrases related to the concept of returning

No Known Activations