INDEX

Explanations

prepositional phrases containing the word 'and'

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases that indicate connections or relationships among ideas or subjects

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ril

-0.71

payer

-0.68

usha

-0.67

BIL

-0.64

resh

-0.63

isive

-0.63

>[

-0.63

elia

-0.63

ocrat

-0.63

trak

-0.62

POSITIVE LOGITS

 elsewhere

1.56

 beyond

1.15

 across

0.94

 abroad

0.94

 throughout

0.94

 anywhere

0.93

 everywhere

0.92

 thereafter

0.88

 onto

0.87

 onwards

0.83

Activations Density 0.423%

prepositional phrases containing the word 'and'

conjunctions and phrases that indicate connections or relationships among ideas or subjects

No Comments

No Known Activations