INDEX

Explanations

proper names, specifically "Harry"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Harry" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PsyNetMessage

-0.88

ourced

-0.71

asio

-0.69

PLA

-0.68

resp

-0.68

IED

-0.66

Ø§ÙĦ

-0.65

-0.63

Filename

-0.63

chnology

-0.62

POSITIVE LOGITS

 Potter

1.40

 Truman

0.87

haus

0.86

 Dresden

0.85

 Styles

0.82

 Fraz

0.79

 Reid

0.76

Tut

0.71

antine

0.71

stones

0.70

Activations Density 0.017%

proper names, specifically "Harry"

mentions of the name "Harry" in various contexts

No Comments

No Known Activations