INDEX

Explanations

mentions of airports

oai_token-act-pair · gpt-3.5-turbo

references to airports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ÑĮ

-0.83

Else

-0.80

vironment

-0.74

vol

-0.71

Beg

-0.71

venth

-0.67

APH

-0.67

andro

-0.66

 Matter

-0.66

aldi

-0.65

POSITIVE LOGITS

 hangar

1.03

 Airport

1.03

 airport

1.02

 airports

0.95

 clearance

0.90

 runway

0.87

 terminal

0.83

 superiority

0.82

 terminals

0.81

 lounge

0.78

Activations Density 0.014%

mentions of airports

references to airports

No Comments

No Known Activations