INDEX

Explanations

phrases indicating something has been modified or altered such as 'sawed-off' or 'bumped-up'

oai_token-act-pair · gpt-3.5-turbo

negative sentiment or criticism related to societal issues

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Tycoon

-0.68

 Vaughn

-0.67

 haunt

-0.67

 Schumer

-0.66

 modification

-0.66

 Grow

-0.66

 Rica

-0.66

 Europa

-0.66

 Schl

-0.66

 charms

-0.65

POSITIVE LOGITS

paren

1.31

upon

1.30

enough

1.24

up

1.23

together

1.22

bodied

1.21

sounding

1.20

looking

1.19

primary

1.17

down

1.13

Activations Density 0.034%

phrases indicating something has been modified or altered such as 'sawed-off' or 'bumped-up'

negative sentiment or criticism related to societal issues

No Comments

No Known Activations