INDEX

Explanations

terms related to the country "Australia"

oai_token-act-pair · gpt-3.5-turbo

references to Australia and related geographical terms

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

aph

-0.71

 McConnell

-0.70

 ellipt

-0.68

 resil

-0.68

 Scha

-0.65

 Clicker

-0.63

 Chattanooga

-0.61

 Kinder

-0.61

Dur

-0.60

 locker

-0.59

POSITIVE LOGITS

ian

1.58

ians

1.55

ia

1.36

IA

1.35

IAN

1.31

istan

1.23

ese

1.21

ESE

1.15

 Islands

1.13

avia

1.12

Activations Density 0.124%

terms related to the country "Australia"

references to Australia and related geographical terms

No Comments

No Known Activations