INDEX

Explanations

phrases related to ongoing activities or advancements

oai_token-act-pair · gpt-3.5-turbo

repeated instances of a specific character or symbol

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

 Shutterstock

-0.72

FML

-0.67

 Quartz

-0.66

 Hungarian

-0.66

 Jewish

-0.65

Orb

-0.65

 Zone

-0.62

 Rack

-0.61

 Quart

-0.60

 Proposition

-0.59

POSITIVE LOGITS

 alike

1.39

 accordingly

1.16

 thereof

1.05

 thereafter

1.00

 thereto

0.96

 therein

0.92

 consequently

0.91

 importantly

0.89

 versa

0.88

depending

0.88

Activations Density 0.288%

phrases related to ongoing activities or advancements

repeated instances of a specific character or symbol

No Comments

No Known Activations