INDEX

Explanations

legal and judicial terms

oai_token-act-pair · gpt-3.5-turbo

judicial proceedings and related terminology

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

DonaldTrump

-0.83

"#

-0.80

cov

-0.75

wcs

-0.73

Americans

-0.70

Washington

-0.67

birth

-0.66

"@

-0.66

amacare

-0.65

Quantity

-0.65

POSITIVE LOGITS

 jurors

1.34

 Judge

1.18

 courtroom

1.17

Judge

1.16

 tribunal

1.15

 jury

1.14

 judge

1.14

 adjourn

1.09

Prosecut

1.09

 Tribunal

1.03

Activations Density 0.268%

legal and judicial terms

judicial proceedings and related terminology

No Comments

No Known Activations