INDEX

Explanations

prepositions or phrases indicating extent or degree

oai_token-act-pair · gpt-3.5-turbo

prepositions and phrases indicating relationships or connections

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ENTS

-0.62

aeda

-0.61

antly

-0.59

apolis

-0.56

DEN

-0.55

arch

-0.55

addafi

-0.55

OV

-0.52

stract

-0.50

ablishment

-0.49

POSITIVE LOGITS

 which

2.13

which

1.83

 whom

1.58

 Which

1.53

Which

1.42

 whose

1.38

whose

1.26

 whence

1.25

 wherein

1.11

 whereby

0.93

Activations Density 0.953%

prepositions or phrases indicating extent or degree

prepositions and phrases indicating relationships or connections

No Comments

No Known Activations