INDEX

Explanations

references to wizards and wizard-related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "wizard" and its variations

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

cdn

-0.81

lihood

-0.80

 cortisol

-0.73

Harris

-0.72

Bra

-0.71

cks

-0.68

 Richardson

-0.65

 Hayes

-0.64

 Kass

-0.64

Sa

-0.64

POSITIVE LOGITS

 Wizard

3.77

 wizard

3.56

 wizards

2.63

izard

1.93

 Sorcerer

1.69

Wiz

1.51

 Wizards

1.47

 sorcerer

1.44

 Hogwarts

1.37

 witch

1.34

Activations Density 0.034%

references to wizards and wizard-related terms

mentions of the word "wizard" and its variations

No Comments

No Known Activations