INDEX

Explanations

words related to utilizing or mobilizing resources/tools or taking action on information

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of utilization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

beard

-0.76

hair

-0.71

oslov

-0.70

 Empires

-0.69

 ethical

-0.67

 publishers

-0.66

 Hust

-0.64

 parents

-0.60

FACE

-0.59

 endif

-0.59

POSITIVE LOGITS

izable

1.33

ised

1.27

izations

1.25

isation

1.23

ization

1.20

izing

1.15

ocated

1.14

izers

1.14

ized

1.14

izes

1.14

Activations Density 0.006%

words related to utilizing or mobilizing resources/tools or taking action on information

words related to the concept of utilization

No Comments

No Known Activations