INDEX

Explanations

mentions of specific names or terms, particularly those related to public figures or locations

oai_token-act-pair · gpt-3.5-turbo

specific names and terms related to individuals and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Democr

-0.80

 prest

-0.75

 Pupp

-0.72

wip

-0.71

 allowances

-0.70

EMS

-0.70

 monop

-0.69

Pax

-0.68

Liberal

-0.68

 socialists

-0.67

POSITIVE LOGITS

opal

2.00

thel

1.77

umar

1.50

 outlet

1.40

anth

1.39

auri

1.30

hari

1.30

ydia

1.22

igor

1.20

anco

1.16

Activations Density 0.053%

mentions of specific names or terms, particularly those related to public figures or locations

specific names and terms related to individuals and entities

No Comments

No Known Activations