INDEX

Explanations

the word "jobs" in various contexts related to employment

oai_token-act-pair · gpt-4-turbo

references to employment and job-related terms

oai_token-act-pair · gpt-3.5-turbo

references to job creation and employment levels

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

gran

-0.74

 Revision

-0.70

 EDITION

-0.70

Push

-0.63

 Edmund

-0.63

 Stev

-0.62

theless

-0.62

 Crom

-0.62

 Flavoring

-0.61

ificant

-0.60

POSITIVE LOGITS

 jobs

0.99

jobs

0.91

hare

0.85

 Jobs

0.84

essions

0.84

hops

0.81

andowski

0.74

afety

0.74

anooga

0.74

ession

0.74

Activations Density 0.028%

the word "jobs" in various contexts related to employment

references to employment and job-related terms

references to job creation and employment levels

No Comments

No Known Activations