INDEX

Explanations

online petitions and related action verbs such as launched, demanding, created, campaigning, rallied, gathered, and petitioning

oai_token-act-pair · gpt-3.5-turbo

terms related to online petitions and activism

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

 pleasures

-0.70

 tastes

-0.67

 Salary

-0.65

 senses

-0.65

 deriv

-0.65

 probabilities

-0.64

 hindsight

-0.64

ulty

-0.62

 flows

-0.61

Ö

-0.60

POSITIVE LOGITS

 boycott

0.86

 advocating

0.85

 vigil

0.84

 hashtag

0.82

 petition

0.81

 protesting

0.80

 denouncing

0.79

 boycot

0.79

 advocacy

0.78

ICE

0.76

Activations Density 0.397%

online petitions and related action verbs such as launched, demanding, created, campaigning, rallied, gathered, and petitioning

terms related to online petitions and activism

No Comments

No Known Activations