INDEX

Explanations

mentions of the country Indonesia

oai_token-act-pair · gpt-3.5-turbo

references to Indonesia in various contexts

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

fare

-0.80

riers

-0.79

hire

-0.78

busters

-0.72

hare

-0.71

VEL

-0.70

ages

-0.69

umbnails

-0.69

abolic

-0.68

abet

-0.68

POSITIVE LOGITS

 Indonesia

0.98

 Airlines

0.95

 Indonesian

0.87

ãħĭ

0.85

 Jakarta

0.85

 Indones

0.83

istani

0.81

 Papua

0.79

 Peoples

0.75

 Lamp

0.75

Activations Density 0.021%

mentions of the country Indonesia

references to Indonesia in various contexts

No Comments

No Known Activations