INDEX

Explanations

prepositions indicating location or direction

oai_token-act-pair · gpt-3.5-turbo

prepositions and phrases indicating relationships or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

theless

-0.86

whether

-0.75

aciously

-0.75

umerous

-0.75

sounding

-0.73

heartedly

-0.72

 accordingly

-0.71

some

-0.70

arently

-0.70

uitous

-0.69

POSITIVE LOGITS

 Borders

1.04

 Poverty

1.03

 Hate

1.03

 Chains

1.02

 Rails

1.02

 Exile

1.02

 Aging

1.02

 Demand

1.01

 Ruin

1.01

 Life

1.01

Activations Density 0.279%

prepositions indicating location or direction

prepositions and phrases indicating relationships or locations

No Comments

No Known Activations