INDEX

Explanations

proper nouns related to the name "Nat"

oai_token-act-pair · gpt-3.5-turbo

the repetition of specific names or terms, particularly the word "Nat" followed by a number

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

wordpress

-0.67

ecause

-0.66

--------------------------------------------------------

-0.64

 contraceptives

-0.62

 Bearing

-0.62

STON

-0.59

dylib

-0.58

poon

-0.57

 upon

-0.57

 highs

-0.56

POSITIVE LOGITS

asha

1.10

acha

1.02

alia

1.00

ivities

0.98

ulia

0.97

ured

0.97

omas

0.96

ivas

0.95

ivity

0.94

iva

0.94

Activations Density 0.052%

proper nouns related to the name "Nat"

the repetition of specific names or terms, particularly the word "Nat" followed by a number

No Comments

No Known Activations