INDEX

Explanations

words related to the workforce and employment

oai_token-act-pair · gpt-3.5-turbo

references to the workforce

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ocular

-0.80

gran

-0.75

osp

-0.73

rous

-0.68

abre

-0.66

rah

-0.65

olic

-0.64

 porous

-0.63

ricular

-0.63

forth

-0.61

POSITIVE LOGITS

 workforce

1.15

 unions

0.72

Builder

0.72

 Quarterly

0.70

 employed

0.70

 unemployed

0.69

 employment

0.68

ãĤ©

0.68

employ

0.67

 multiplier

0.67

Activations Density 0.009%

words related to the workforce and employment

references to the workforce

No Comments

No Known Activations