INDEX

Explanations

terms related to railways

oai_token-act-pair · gpt-3.5-turbo

references to railway systems and infrastructure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Parenthood

-0.80

 Ambrose

-0.76

osi

-0.73

 Homo

-0.71

 Hague

-0.67

 Naomi

-0.66

 Holder

-0.63

umer

-0.62

 Chomsky

-0.62

 bleach

-0.62

POSITIVE LOGITS

roads

1.60

road

1.11

ways

1.04

cars

1.00

craft

0.95

 stations

0.90

 freight

0.89

 locom

0.89

liner

0.88

car

0.87

Activations Density 0.019%

terms related to railways

references to railway systems and infrastructure

No Comments

No Known Activations