INDEX

Explanations

proper nouns related to the name "Lewis."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Lewis"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

zeb

-0.77

UID

-0.71

 incub

-0.67

-0.65

snap

-0.65

apt

-0.64

SAP

-0.62

 vampire

-0.61

pan

-0.61

 disposable

-0.60

POSITIVE LOGITS

 Lewis

3.83

Lewis

3.12

 Carroll

1.34

 Elliott

1.31

 Stewart

1.30

Hamilton

1.29

 Floyd

1.28

 Phelps

1.25

 Higgins

1.24

Lee

1.22

Activations Density 0.016%

proper nouns related to the name "Lewis."

occurrences of the name "Lewis"

No Comments

No Known Activations