INDEX

Explanations

nothing, as it did not activate for any content

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

Code, parentheses, or special characters

np_acts-logits-general · gemini-2.0-flash

code and technical jargon

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 StatefulWidget

-0.84

lorette

-0.75

bootstrapcdn

-0.73

енча

-0.68

 itſelf

-0.64

SequentialGroup

-0.64

 vectorstock

-0.64

webElement

-0.64

 NDEBUG

-0.63

moiselle

-0.63

POSITIVE LOGITS

↵↵

0.57

0.49

0.47

'])

0.47

subpackage

0.46

'],

0.45

 ofrec

0.44

'])

0.44

The

0.43

</h3>

0.41

Activations Density 0.053%

nothing, as it did not activate for any content

Code, parentheses, or special characters

code and technical jargon

No Comments

No Known Activations