INDEX

Explanations

acronyms related to organizations or associations

oai_token-act-pair · gpt-3.5-turbo

references to the abbreviation "MA" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 friction

-0.69

 underdog

-0.68

 contr

-0.67

 Garrett

-0.66

 escaped

-0.66

 fled

-0.62

 halftime

-0.62

 Sponge

-0.61

 escaping

-0.60

 rebellious

-0.60

POSITIVE LOGITS

MA

4.21

MA

1.83

ma

1.63

EMA

1.61

ME

1.52

MO

1.52

CA

1.43

MI

1.38

MAS

1.37

BA

1.34

Activations Density 0.011%

acronyms related to organizations or associations

references to the abbreviation "MA" in various contexts

No Comments

No Known Activations