INDEX

Explanations

mentions of the term "Master"

oai_token-act-pair · gpt-3.5-turbo

references to the term "Master."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olson

-0.79

ÄŁ

-0.74

hern

-0.71

idth

-0.70

pse

-0.70

poll

-0.70

 iodine

-0.67

lihood

-0.67

 balloons

-0.66

ĺħ

-0.66

POSITIVE LOGITS

 Master

3.70

Master

2.95

 master

2.51

 Masters

2.30

master

2.24

 masters

2.09

masters

1.91

 Mastery

1.49

 Mistress

1.43

MAS

1.34

Activations Density 0.010%

mentions of the term "Master"

references to the term "Master."

No Comments

No Known Activations