INDEX

Explanations

Nin-related terms, possibly referring to the word "Ninja."

oai_token-act-pair · gpt-3.5-turbo

references to "Nin" or "ninja" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

inventoryQuantity

-0.76

ASC

-0.68

 Miranda

-0.67

 mileage

-0.66

 COUNTY

-0.66

 carriers

-0.65

HIP

-0.64

 PRESS

-0.63

 DRAG

-0.63

 Hilton

-0.62

POSITIVE LOGITS

eteen

1.87

eteenth

1.67

eties

1.52

ety

1.41

jas

1.41

jah

1.14

ovember

1.10

ja

1.09

ormal

1.07

omore

1.01

Activations Density 0.013%

Nin-related terms, possibly referring to the word "Ninja."

references to "Nin" or "ninja" in various contexts

No Comments

No Known Activations