INDEX

Explanations

references to the name "Lawrence."

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Lawrence"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ramid

-0.89

raid

-0.88

resso

-0.88

izoph

-0.87

hedral

-0.83

joined

-0.80

cffff

-0.80

tnc

-0.78

arers

-0.75

requ

-0.74

POSITIVE LOGITS

 Lawrence

0.94

 Liver

0.94

ville

0.91

 Berkeley

0.87

 Hague

0.79

 Foster

0.79

burg

0.78

ç·

0.78

Wel

0.78

Kra

0.77

Activations Density 0.022%

references to the name "Lawrence."

mentions of the name "Lawrence"

No Comments

No Known Activations