INDEX

Explanations

mentions of a specific location - "Detroit"

oai_token-act-pair · gpt-3.5-turbo

references to the term "Detroit."

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

xual

-0.88

manship

-0.78

nown

-0.75

ammy

-0.70

blind

-0.69

lihood

-0.68

drive

-0.67

 actionGroup

-0.67

 mileage

-0.65

 Decay

-0.64

POSITIVE LOGITS

ector

1.27

ective

1.22

achment

1.09

ected

1.08

ention

1.03

ailed

1.03

roit

1.01

ection

1.00

rans

0.96

eret

0.95

Activations Density 0.029%

mentions of a specific location - "Detroit"

references to the term "Detroit."

No Comments

No Known Activations