INDEX

Explanations

prepositions followed by an object

oai_token-act-pair · gpt-3.5-turbo

prepositions and their usages in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Īè

-0.63

 herein

-0.61

ï¸ı

-0.58

ACY

-0.56

Enlarge

-0.55

 therein

-0.54

IZ

-0.53

NH

-0.52

Neil

-0.52

ãĤ´

-0.52

POSITIVE LOGITS

adows

0.71

sembly

0.68

orage

0.65

ilings

0.65

 Windsor

0.64

xon

0.62

 pony

0.62

arers

0.62

orney

0.61

pher

0.61

Activations Density 1.024%

prepositions followed by an object

prepositions and their usages in context

No Comments

No Known Activations