INDEX

Explanations

quantitative information related to income and statistics in text

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.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

worms

-0.72

choes

-0.70

 facult

-0.69

=-=-=-=-

-0.67

into

-0.67

IGHTS

-0.67

Revolution

-0.66

matic

-0.65

 feder

-0.65

glers

-0.65

POSITIVE LOGITS

 household

0.92

 income

0.89

 Income

0.86

 Household

0.78

 incomes

0.76

 median

0.73

 sized

0.73

wealth

0.69

ered

0.68

 Median

0.67

Activations Density 0.017%

quantitative information related to income and statistics in text

No Comments

No Known Activations