INDEX

Explanations

legal and political terms related to international agreements and laws

oai_token-act-pair · gpt-3.5-turbo

legal and political terminology related to formal agreements and regulations

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

 Milwaukee

-0.75

 Fresno

-0.70

 Wisconsin

-0.69

 Packers

-0.69

Wisconsin

-0.69

 Seattle

-0.68

 Pittsburgh

-0.66

Colorado

-0.66

 Prescott

-0.65

Veter

-0.64

POSITIVE LOGITS

bourg

0.88

 decre

0.84

 envis

0.84

 decree

0.82

 authorised

0.77

 favourable

0.77

 UNESCO

0.76

0.75

 enacted

0.75

 unanimously

0.74

Activations Density 0.177%

legal and political terms related to international agreements and laws

legal and political terminology related to formal agreements and regulations

No Comments

No Known Activations