INDEX

Explanations

references to the name "Jennifer"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Jennifer."

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

holders

-0.85

holder

-0.75

 nomine

-0.73

alion

-0.69

ngth

-0.66

atively

-0.65

itious

-0.65

enhagen

-0.64

 administr

-0.64

liest

-0.64

POSITIVE LOGITS

 Lawrence

0.95

 Lopez

0.92

issance

0.89

 Walters

0.88

Doe

0.85

 Jacobs

0.83

anna

0.82

 Garner

0.81

 Hudson

0.80

 Grey

0.80

Activations Density 0.016%

references to the name "Jennifer"

mentions of the name "Jennifer."

No Comments

No Known Activations