INDEX

Explanations

mentions of monetary earnings

oai_token-act-pair · gpt-3.5-turbo

terms related to income and earnings

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

 Franz

-0.66

Jess

-0.65

 Ukrain

-0.62

 Strait

-0.61

pn

-0.61

 Prol

-0.60

Yel

-0.59

bru

-0.59

 Balkans

-0.58

Bru

-0.58

POSITIVE LOGITS

 earners

0.98

 income

0.98

 earn

0.95

 earning

0.95

Earn

0.94

 incomes

0.94

 payroll

0.88

 Income

0.85

 Earn

0.83

 earnings

0.83

Activations Density 0.047%

mentions of monetary earnings

terms related to income and earnings

No Comments

No Known Activations