INDEX

Explanations

any use of the word "demo"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "demo" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

turn

-0.74

CHAPTER

-0.70

leans

-0.66

adia

-0.65

Else

-0.64

metic

-0.64

ophical

-0.63

 Encyclopedia

-0.63

laus

-0.62

 unsolved

-0.62

POSITIVE LOGITS

 demo

0.92

eer

0.89

psey

0.89

 demos

0.87

 reel

0.76

eers

0.76

 taped

0.73

stration

0.73

ery

0.72

 presentation

0.71

Activations Density 0.017%

any use of the word "demo"

occurrences of the word "demo" and its variations

No Comments

No Known Activations