INDEX

Explanations

the term "Bay Area"

oai_token-act-pair · gpt-3.5-turbo

references to the Bay Area

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

etsk

-1.00

vous

-0.91

soDeliveryDate

-0.88

wcsstore

-0.80

 Cosponsors

-0.78

named

-0.77

days

-0.77

actionDate

-0.76

SK

-0.75

clinton

-0.74

POSITIVE LOGITS

 Area

0.90

 Rapid

0.89

 Peninsula

0.83

 Development

0.76

 Extension

0.76

 Controller

0.73

 Regional

0.71

 Developers

0.69

 Planning

0.69

 Connection

0.68

Activations Density 0.012%

the term "Bay Area"

references to the Bay Area

No Comments

No Known Activations