INDEX

Explanations

government agencies and related terms

oai_token-act-pair · gpt-3.5-turbo

acronyms and abbreviations related to government agencies and organizations

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

lihood

-0.94

bery

-0.80

 Australians

-0.78

 Tasman

-0.77

 Mechdragon

-0.75

 Ender

-0.75

amins

-0.74

acters

-0.73

Tsu

-0.71

 Samurai

-0.70

POSITIVE LOGITS

 councill

0.89

HQ

0.87

USD

0.82

inventoryQuantity

0.77

ERG

0.77

 FEMA

0.77

senal

0.77

 payroll

0.75

 administrator

0.73

EMA

0.73

Activations Density 0.022%

government agencies and related terms

acronyms and abbreviations related to government agencies and organizations

No Comments

No Known Activations