INDEX

Explanations

editorial titles or positions within a news organization

oai_token-act-pair · gpt-3.5-turbo

phrases related to editorial positions and titles

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

yip

-0.74

llah

-0.70

akeru

-0.70

urst

-0.67

tu

-0.67

 sche

-0.67

 medic

-0.66

oleon

-0.65

ritis

-0.65

 reconnect

-0.65

POSITIVE LOGITS

Journal

0.99

Publisher

0.95

 Editorial

0.86

Edge

0.81

âĸ¬

0.78

pse

0.78

 Picks

0.76

 Editors

0.74

lishing

0.74

×©

0.72

Activations Density 0.127%

editorial titles or positions within a news organization

phrases related to editorial positions and titles

No Comments

No Known Activations