INDEX

Explanations

words related to employment and work

oai_token-act-pair · gpt-3.5-turbo

references to employment and job roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Flavoring

-0.80

 EDITION

-0.75

ificant

-0.64

Oo

-0.63

 Stev

-0.63

 Bulg

-0.63

 elaborate

-0.63

66666666

-0.62

Push

-0.62

orp

-0.61

POSITIVE LOGITS

job

0.95

job

0.91

 jobs

0.85

jobs

0.81

washer

0.81

anooga

0.76

Job

0.74

awaru

0.71

 Simulator

0.71

 killer

0.71

Activations Density 0.039%

words related to employment and work

references to employment and job roles

No Comments

No Known Activations