INDEX

Explanations

instances of the word "legitimacy" and related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to legitimacy and its related concepts

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

Heart

-0.70

 Rain

-0.66

OTOS

-0.62

trap

-0.62

 Growth

-0.60

 gust

-0.60

Spot

-0.60

 Mild

-0.60

 Grove

-0.59

Lens

-0.58

POSITIVE LOGITS

 legitimacy

0.99

 legitim

0.88

AFTA

0.87

acies

0.86

DragonMagazine

0.85

 credentials

0.84

abil

0.83

 conferred

0.82

ignty

0.80

clinton

0.80

Activations Density 0.029%

instances of the word "legitimacy" and related terms

terms related to legitimacy and its related concepts

No Comments

No Known Activations