INDEX

Explanations

phrases related to job descriptions or duties

oai_token-act-pair · gpt-3.5-turbo

references to various jobs or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Flavoring

-0.83

 Bulg

-0.74

Oo

-0.73

++++

-0.68

stals

-0.67

orp

-0.65

anwhile

-0.64

 Blast

-0.63

 EDITION

-0.63

Ft

-0.62

POSITIVE LOGITS

job

0.82

 sched

0.82

 seeker

0.76

 Simulator

0.75

job

0.74

 jobs

0.73

apixel

0.72

 postings

0.72

 ethic

0.71

anooga

0.71

Activations Density 0.042%

phrases related to job descriptions or duties

references to various jobs or roles

No Comments

No Known Activations