INDEX

Explanations

information related to the amount of time someone has spent in a particular place or position

oai_token-act-pair · gpt-3.5-turbo

phrases indicating duration or time spent in a particular activity or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

iru

-0.79

ucker

-0.71

lees

-0.71

endif

-0.70

aults

-0.67

Adds

-0.63

ioned

-0.62

illin

-0.61

 pile

-0.61

arget

-0.59

POSITIVE LOGITS

 seven

1.21

 eight

1.20

 nine

1.19

 seventeen

1.16

six

1.16

 decades

1.15

 five

1.15

 fourteen

1.14

 eighteen

1.14

 thirty

1.13

Activations Density 0.142%

information related to the amount of time someone has spent in a particular place or position

phrases indicating duration or time spent in a particular activity or context

No Comments

No Known Activations