INDEX

Explanations

terms related to indexing, such as words like "index" and actions related to creating or comparing indexes

oai_token-act-pair · gpt-3.5-turbo

mentions of "index" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

soDeliveryDate

-0.88

 Honour

-0.73

isSpecialOrderable

-0.69

zech

-0.67

uggage

-0.67

creen

-0.66

atu

-0.65

sei

-0.65

 behav

-0.64

overs

-0.63

POSITIVE LOGITS

 mund

0.91

ical

0.82

 finger

0.81

icals

0.80

alist

0.77

uary

0.76

uated

0.76

rix

0.75

ered

0.75

ured

0.74

Activations Density 0.051%

terms related to indexing, such as words like "index" and actions related to creating or comparing indexes

mentions of "index" in various contexts

No Comments

No Known Activations