INDEX

Explanations

references to job-related tasks and responsibilities

oai_token-act-pair · gpt-3.5-turbo

references to "job" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

-0.83

 Bulg

-0.74

orp

-0.72

 EDITION

-0.68

 Stev

-0.66

++++

-0.65

stals

-0.63

pac

-0.62

vari

-0.61

 Revision

-0.61

POSITIVE LOGITS

 sched

0.79

 jobs

0.78

job

0.77

job

0.74

ername

0.74

 ethic

0.74

 kicker

0.73

 duties

0.73

 title

0.72

 titles

0.70

Activations Density 0.029%

references to job-related tasks and responsibilities

references to "job" in various contexts

No Comments

No Known Activations