INDEX

Explanations

references to geopolitical relationships and analyses of foreign policy

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

Followed by organizations or job titles

np_acts-logits-general · gemini-2.0-flash

institutions and organizations analysed

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

 expéri

-0.46

 luch

-0.41

Spoljašnje

-0.40

 clinically

-0.39

 befre

-0.38

 derra

-0.37

 entertainer

-0.37

 terap

-0.36

 tunt

-0.36

чай

-0.36

POSITIVE LOGITS

ValueStyle

0.94

 Brookings

0.90

 analyst

0.89

 think

0.87

 analysts

0.83

Analyst

0.82

 Policy

0.81

 Analyst

0.80

 Eurasia

0.80

 analysis

0.79

Activations Density 0.204%

references to geopolitical relationships and analyses of foreign policy

Followed by organizations or job titles

institutions and organizations analysed

No Comments

No Known Activations