INDEX

Explanations

phrases or sentences containing the word "labeled" or "labelled" followed by a specific descriptor

oai_token-act-pair · gpt-3.5-turbo

instances of the word "labelled" or its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

itars

-0.78

psons

-0.72

vati

-0.66

cession

-0.66

ixture

-0.65

 Deliver

-0.64

asin

-0.64

vous

-0.63

birth

-0.63

zzo

-0.61

POSITIVE LOGITS

 labelled

1.12

 labeled

1.10

TextColor

0.76

 branded

0.75

deck

0.71

label

0.70

marked

0.70

 labeling

0.69

 è£ıè

0.69

paralle

0.68

Activations Density 0.009%

phrases or sentences containing the word "labeled" or "labelled" followed by a specific descriptor

instances of the word "labelled" or its variations

No Comments

No Known Activations