INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

plural nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 seas

-0.72

£ı

-0.70

OSP

-0.67

 Labour

-0.62

FINE

-0.62

 Seas

-0.62

 Rothschild

-0.61

 Berks

-0.61

Rih

-0.60

 Lanc

-0.59

POSITIVE LOGITS

ources

1.14

ourced

1.10

aturated

1.01

ourcing

1.01

wered

1.01

olutions

0.95

olving

0.95

atellite

0.94

pecially

0.92

hip

0.91

Activations Density 0.149%

proper nouns

plural nouns

No Comments

No Known Activations