INDEX

Explanations

mentions of drum-related terms and actions

oai_token-act-pair · gpt-3.5-turbo

references to drums and drumming-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

-0.75

 Upton

-0.65

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

-0.64

Kiw

-0.64

hiro

-0.62

 Morales

-0.61

 Australians

-0.61

 Mandela

-0.60

 Hitman

-0.59

 Tasman

-0.59

POSITIVE LOGITS

 drums

1.08

 drum

1.05

mers

0.98

ming

0.95

sticks

0.94

beat

0.90

ette

0.90

sonian

0.89

 Drum

0.84

ettes

0.84

Activations Density 0.010%

mentions of drum-related terms and actions

references to drums and drumming-related concepts

No Comments

No Known Activations