INDEX

Explanations

references related to the number 9 and potentially the term "Ninja"

oai_token-act-pair · gpt-3.5-turbo

references to "Nin" or variations of it, indicating a connection to something related to "Ninja"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ASC

-0.75

 Miranda

-0.68

ansas

-0.65

 mileage

-0.65

 Hilton

-0.63

 DRAG

-0.62

 placement

-0.61

Pwr

-0.60

 PRESS

-0.60

HIP

-0.59

POSITIVE LOGITS

eteen

1.88

eteenth

1.74

eties

1.54

ety

1.40

jas

1.40

ovember

1.13

ormal

1.08

jah

1.05

omore

1.03

ja

1.01

Activations Density 0.016%

references related to the number 9 and potentially the term "Ninja"

references to "Nin" or variations of it, indicating a connection to something related to "Ninja"

No Comments

No Known Activations