INDEX

Explanations

mentions of different groups of people

oai_token-act-pair · gpt-3.5-turbo

references to groups of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

tains

-0.88

opens

-0.71

iHUD

-0.70

¿½

-0.68

Increases

-0.68

manent

-0.67

 Flavoring

-0.67

CONT

-0.65

forestation

-0.63

 Prel

-0.63

POSITIVE LOGITS

 aren

1.57

 deserve

1.55

ARE

1.36

 weren

1.33

 shouldn

1.32

are

1.32

 despise

1.30

don

1.29

ain

1.28

 suck

1.28

Activations Density 0.421%

mentions of different groups of people

references to groups of people

No Comments

No Known Activations