INDEX

Explanations

phrases related to aviation incidents, such as specific flight numbers and related events

oai_token-act-pair · gpt-3.5-turbo

references to specific airline incidents and flights

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

arious

-0.76

å¥³

-0.73

laus

-0.70

Jah

-0.68

onom

-0.68

onomy

-0.65

 flourish

-0.65

kai

-0.65

SPONSORED

-0.65

alist

-0.64

POSITIVE LOGITS

 airliner

1.23

 Flight

0.98

Flight

0.94

 passengers

0.90

 wreckage

0.87

 Airlines

0.86

 Lumpur

0.85

 crashed

0.84

 passenger

0.83

 Boeing

0.82

Activations Density 0.069%

phrases related to aviation incidents, such as specific flight numbers and related events

references to specific airline incidents and flights

No Comments

No Known Activations