INDEX

Explanations

neural network layers and activations

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inel

-0.09

unl

-0.09

bons

-0.09

 torchvision

-0.09

 superClass

-0.09

 Schiff

-0.09

éĹ»

-0.09

ater

-0.08

 Torch

-0.08

 Abed

-0.08

POSITIVE LOGITS

alth

0.10

.relu

0.09

relu

0.09

 Dense

0.09

utf

0.09

rve

0.09

adam

0.09

ritz

0.09

 identity

0.09

 medi

0.09

Activations Density 0.018%