INDEX

Explanations

business-related words and phrases

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Ô

-0.78

 sqor

-0.68

actionDate

-0.68

ventus

-0.67

 Lanka

-0.66

noon

-0.66

SpaceEngineers

-0.66

sbm

-0.65

azeera

-0.64

 Consent

-0.63

POSITIVE LOGITS

 considers

1.01

 intends

1.00

 expects

0.99

 itself

0.98

 believes

0.98

 maintains

0.98

 opted

0.96

 relies

0.95

's

0.95

 strives

0.93

Activations Density 0.199%

business-related words and phrases

No Comments

No Known Activations