INDEX

Explanations

references to US Supreme Court Justices

oai_token-act-pair · gpt-3.5-turbo

references to justices and their opinions in a legal context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ramid

-0.74

FTWARE

-0.70

tenance

-0.69

ghai

-0.69

wx

-0.69

wagen

-0.67

 Mayhem

-0.67

bsite

-0.66

 Kickstarter

-0.66

 Pyramid

-0.66

POSITIVE LOGITS

 Scalia

1.50

otom

1.33

 dissent

1.32

 Gins

1.28

 dissenting

1.26

 Sonia

1.05

 justices

1.05

 Elena

1.02

 Gorsuch

1.02

 diss

1.00

Activations Density 0.134%

references to US Supreme Court Justices

references to justices and their opinions in a legal context

No Comments

No Known Activations