INDEX

Explanations

references to social media and online engagement

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

Tokens after social media mentions

np_acts-logits-general · gemini-2.0-flash

social media follows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ex

-0.53

tyg

-0.48

CSRF

-0.45

وفق

-0.44

 vulgaires

-0.44

Ex

-0.43

herself

-0.41

nesc

-0.41

 tadi

-0.41

azt

-0.41

POSITIVE LOGITS

 Twitter

1.03

 twitter

1.03

(@

1.00

0.99

Twitter

0.99

twitter

0.99

[@

0.89

 tweets

0.87

 tweeting

0.86

 facebook

0.86

Activations Density 0.083%

references to social media and online engagement

Tokens after social media mentions

social media follows

No Comments

No Known Activations