INDEX

Explanations

mentions of the name "Simon" at a high level of activation

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Simon."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

olulu

-0.73

00200000

-0.72

reek

-0.72

late

-0.71

eals

-0.70

merce

-0.69

doors

-0.67

ktop

-0.67

rings

-0.66

laws

-0.66

POSITIVE LOGITS

 Simon

1.16

Simon

1.08

 Says

0.80

 Richie

0.79

 Gerr

0.79

 Fraser

0.73

irtual

0.73

 Baron

0.72

zman

0.72

Baz

0.72

Activations Density 0.007%

mentions of the name "Simon" at a high level of activation

mentions of the name "Simon."

No Comments

No Known Activations