INDEX

Explanations

references to technology companies and related terms

oai_token-act-pair · gpt-3.5-turbo

references to technology and data-related concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 loophole

-0.73

jri

-0.71

ilant

-0.66

 workaround

-0.64

ossibility

-0.63

 vomiting

-0.61

 Beware

-0.60

 hesitation

-0.60

 loopholes

-0.59

 caveat

-0.58

POSITIVE LOGITS

 civilisation

0.67

oplan

0.66

 galaxies

0.65

Merit

0.64

NRL

0.62

 humankind

0.61

wealth

0.61

 empires

0.60

 Hearthstone

0.60

asonry

0.60

Activations Density 1.128%

references to technology companies and related terms

references to technology and data-related concepts

No Comments

No Known Activations