INDEX

Explanations

names of political figures or leaders

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

the name "Prabhu" and related variations or mentions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

 litter

-0.68

 Referred

-0.66

 commencement

-0.65

 prost

-0.64

 modified

-0.63

 Secondly

-0.63

 desk

-0.62

 consequential

-0.61

 loud

-0.61

 wise

-0.61

POSITIVE LOGITS

atche

1.63

udence

1.46

ingle

1.36

ussia

1.34

ussian

1.31

indle

1.21

achu

1.20

ayers

1.20

isc

1.16

ima

1.16

Activations Density 0.013%

names of political figures or leaders

the name "Prabhu" and related variations or mentions

No Comments

No Known Activations