INDEX

Explanations

the letter "E" followed by other uppercase letters, likely related to the format of citations

oai_token-act-pair · gemini-2.0-flash

E

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

on

-0.53

ither

-0.50

志

-0.49

vent

-0.49

-0.47

pr

-0.46

for

-0.45

pre

-0.45

Mer

-0.45

mer

-0.45

POSITIVE LOGITS

 HasFactory

0.93

 esternos

0.83

 للاسماء

0.81

AndEndTag

0.70

."));

0.70

principalColumn

0.69

 utafiti

0.69

+:+

0.68

IUrlHelper

0.65

🏻‍♀️

0.65

Activations Density 0.414%

the letter "E" followed by other uppercase letters, likely related to the format of citations

E

No Comments

No Known Activations