INDEX

Explanations

the specific term "Insiders" or variations of it

oai_token-act-pair · gpt-3.5-turbo

instances of the term "Ins" and its variations occurring frequently in the text

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

âĢ¢âĢ¢

-0.76

DragonMagazine

-0.75

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.73

AUT

-0.72

EStream

-0.72

ãĥ£

-0.71

>>>>>>>>

-0.69

âĺħâĺħ

-0.68

dylib

-0.67

WARE

-0.67

POSITIVE LOGITS

ufficient

1.16

urrection

1.02

iders

1.01

ights

0.99

urance

0.92

ulin

0.90

ensibly

0.87

ider

0.85

idious

0.85

urg

0.84

Activations Density 0.006%

the specific term "Insiders" or variations of it

instances of the term "Ins" and its variations occurring frequently in the text

No Comments

No Known Activations