INDEX

Explanations

references to judges

oai_token-act-pair · gpt-3.5-turbo

references to judges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

usp

-0.81

uld

-0.74

ijk

-0.72

ulates

-0.71

eworld

-0.71

irst

-0.67

haar

-0.65

ulated

-0.64

iliar

-0.63

td

-0.62

POSITIVE LOGITS

 Judge

0.98

Judge

0.94

 Advocate

0.89

 Gorsuch

0.84

jud

0.83

istrate

0.82

 Judy

0.77

orneys

0.76

yers

0.76

 rulings

0.75

Activations Density 0.005%

references to judges

references to judges

No Comments

No Known Activations