INDEX

Explanations

numeric values, dates, and measurements

oai_token-act-pair · gpt-3.5-turbo

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

ãĥ³ãĤ¸

-0.71

<?

-0.69

Topic

-0.68

Reply

-0.67

ntil

-0.65

pse

-0.64

ãĤ¤ãĥĪ

-0.64

DragonMagazine

-0.62

quote

-0.61

kef

-0.60

POSITIVE LOGITS

 arrives

0.92

 expires

0.87

 airs

0.83

 ceases

0.82

 enters

0.81

 reaches

0.81

 arrived

0.80

 existed

0.80

 finishes

0.80

 completes

0.80

Activations Density 0.541%

numeric values, dates, and measurements

No Comments

No Known Activations