INDEX

Explanations

terms or phrases related to divisions or separations

oai_token-act-pair · gpt-3.5-turbo

instances of the concept of division or disparity 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 @ 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

oken

-0.83

vez

-0.68

rouse

-0.64

OD

-0.63

aimon

-0.63

ark

-0.62

perty

-0.62

ãĥīãĥ©

-0.62

 Written

-0.61

amina

-0.61

POSITIVE LOGITS

 divides

1.12

 divide

1.09

naire

0.97

 Divide

0.83

 dividing

0.83

 pits

0.76

 divisions

0.74

 divid

0.73

Split

0.72

otomy

0.72

Activations Density 0.014%

terms or phrases related to divisions or separations

instances of the concept of division or disparity in various contexts

No Comments

No Known Activations