INDEX

Explanations

drums or drum-related terms

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "drum" or variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Agency

-0.71

 Tasman

-0.69

 Mandela

-0.68

Kiw

-0.67

hiro

-0.64

 Pref

-0.61

################

-0.60

 preferential

-0.59

 Upton

-0.59

 Morales

-0.58

POSITIVE LOGITS

mers

1.29

ming

1.16

sonian

1.07

nas

1.03

beat

1.01

sticks

0.94

staff

0.92

mond

0.91

stick

0.90

 drum

0.86

Activations Density 0.024%

drums or drum-related terms

the presence of the word "drum" or variations of it

No Comments

No Known Activations