INDEX

Explanations

names of specific judicial figures and related legal terms

oai_token-act-pair · gpt-3.5-turbo

mentions of justices 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orama

-0.73

unity

-0.72

Ã§

-0.71

bsite

-0.69

 Mayhem

-0.68

 destro

-0.65

yrinth

-0.65

andals

-0.64

egu

-0.64

gotten

-0.63

POSITIVE LOGITS

 Scalia

1.33

 Gins

1.08

 justices

1.00

 Sonia

0.97

 dissenting

0.96

 dissent

0.91

otom

0.88

Jud

0.87

 Brennan

0.87

 Elena

0.85

Activations Density 0.070%

names of specific judicial figures and related legal terms

mentions of justices in a legal context

No Comments

No Known Activations