INDEX

Explanations

phrases related to software demonstrations

oai_token-act-pair · gpt-3.5-turbo

references to "demo" or demonstrations of products or software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

turn

-0.81

Else

-0.73

CHAPTER

-0.69

leans

-0.67

ricanes

-0.66

luster

-0.65

metic

-0.65

aws

-0.64

ãĤ·ãĥ£

-0.64

laus

-0.63

POSITIVE LOGITS

 demo

0.90

 demos

0.82

eer

0.81

psey

0.81

 reel

0.74

 Demo

0.73

 taped

0.72

 coupon

0.71

eers

0.69

pled

0.68

Activations Density 0.017%

phrases related to software demonstrations

references to "demo" or demonstrations of products or software

No Comments

No Known Activations