INDEX

Explanations

references to 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vol

-0.72

thood

-0.71

omething

-0.70

hesis

-0.69

ophers

-0.68

vironment

-0.68

acity

-0.68

ÑĮ

-0.67

terday

-0.66

 Matter

-0.66

POSITIVE LOGITS

 hangar

1.19

 airport

1.02

 Airport

1.00

 terminal

0.99

 airports

0.99

 terminals

0.98

 Terminal

0.96

 Authority

0.94

 runway

0.90

 lounge

0.88

Activations Density 0.036%

references to airports

references to airports

No Comments

No Known Activations