INDEX

Explanations

mentions of employers or employment-related terms

oai_token-act-pair · gpt-3.5-turbo

references to employers and employment-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 sheer

-0.67

BST

-0.67

-0.65

range

-0.64

Push

-0.63

 Flavoring

-0.62

voy

-0.61

yss

-0.61

 Grip

-0.61

 Revival

-0.59

POSITIVE LOGITS

employ

1.03

 employer

1.02

 Employ

0.96

 employers

0.95

Employ

0.82

 unions

0.76

chwitz

0.76

 advertis

0.76

 employee

0.73

 Advantage

0.72

Activations Density 0.018%

mentions of employers or employment-related terms

references to employers and employment-related contexts

No Comments

No Known Activations