INDEX

Explanations

prepositions followed by verbs describing appearance or occurrence

oai_token-act-pair · gpt-3.5-turbo

instances of the word "in" commonly associated with contexts of location or inclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

NOW

-0.71

stroke

-0.69

aido

-0.68

ãĥĦ

-0.66

UME

-0.64

icz

-0.63

ido

-0.63

ideo

-0.62

stall

-0.62

ZA

-0.61

POSITIVE LOGITS

effic

1.17

clusions

1.10

 conjunction

1.10

ordinate

1.06

animate

1.05

 lieu

1.03

 relation

1.03

escap

0.97

 situ

0.97

organic

0.96

Activations Density 0.260%

prepositions followed by verbs describing appearance or occurrence

instances of the word "in" commonly associated with contexts of location or inclusion

No Comments

No Known Activations