INDEX

Explanations

dollar amounts representing annual figures

oai_token-act-pair · gpt-3.5-turbo

references to monetary amounts associated with yearly income or expenditures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

achus

-0.88

ropy

-0.68

ropolitan

-0.66

heon

-0.65

hod

-0.64

aleb

-0.64

appings

-0.63

enth

-0.62

kef

-0.62

aunch

-0.61

POSITIVE LOGITS

 thereafter

1.00

ago

0.94

/$

0.82

ilion

0.74

 (Â£

0.73

rent

0.72

long

0.71

cium

0.71

bil

0.70

wage

0.70

Activations Density 0.040%

dollar amounts representing annual figures

references to monetary amounts associated with yearly income or expenditures

No Comments

No Known Activations