INDEX

Explanations

mentions of locations or organizations with 'Bay' in their name

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

mble

-0.78

etsk

-0.74

matter

-0.68

iferation

-0.66

urally

-0.64

×ķ

-0.64

anson

-0.62

 Luthor

-0.62

uania

-0.61

eg

-0.60

POSITIVE LOGITS

onet

1.24

esian

1.13

 Area

0.81

town

0.77

olla

0.76

leigh

0.75

Bay

0.74

ou

0.73

Bay

0.72

 Buccaneers

0.71

Activations Density 0.020%

mentions of locations or organizations with 'Bay' in their name

references to the Bay Area

No Comments

No Known Activations