INDEX

Explanations

references to wage-related terms and employment conditions

oai_token-act-pair · gpt-3.5-turbo

mentions of wage-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

obyl

-0.88

-0.80

umbn

-0.72

ctica

-0.71

 Chimera

-0.69

olog

-0.69

Jub

-0.68

 Blossom

-0.67

ergy

-0.67

orage

-0.67

POSITIVE LOGITS

 earners

1.26

wage

1.08

 labor

1.00

 labour

0.98

 wage

0.95

 labou

0.94

 wages

0.88

 laborers

0.87

checks

0.86

 stagnation

0.80

Activations Density 0.021%

references to wage-related terms and employment conditions

mentions of wage-related concepts

No Comments

No Known Activations