INDEX

Explanations

Latin or medical terms related to specific anatomical structures, medical conditions, and medical treatments

oai_token-act-pair · gpt-3.5-turbo

the term 'count' or related expressions that reference counts or quantities

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

DonaldTrump

-0.75

Ô

-0.75

Downloadha

-0.67

UNCH

-0.67

 challeng

-0.67

ACP

-0.63

 Mandela

-0.63

BILITY

-0.62

visor

-0.62

 mosqu

-0.61

POSITIVE LOGITS

rees

1.19

ools

1.07

urn

1.02

inct

0.98

acular

0.96

rix

0.95

eenth

0.95

ree

0.95

ypes

0.95

ype

0.92

Activations Density 0.016%

Latin or medical terms related to specific anatomical structures, medical conditions, and medical treatments

the term 'count' or related expressions that reference counts or quantities

No Comments

No Known Activations