INDEX

Explanations

content related to social media engagement and interactions

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

Code or markup-related texts

np_acts-logits-general · gemini-2.0-flash

twitter posts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 capito

-0.57

таратура

-0.57

mybatisplus

-0.50

УДК

-0.46

 favoris

-0.45

')}}"

-0.45

Mutagenicity

-0.44

ümüş

-0.43

IsMutable

-0.43

 kapas

-0.42

POSITIVE LOGITS

pic

1.00

 twitter

0.78

—

0.77

pic

0.76

 tweet

0.73

 Tweet

0.73

(@

0.72

 tweeted

0.72

 tweets

0.70

 Tweets

0.69

Activations Density 0.074%

content related to social media engagement and interactions

Code or markup-related texts

twitter posts

No Comments

No Known Activations