INDEX

Explanations

concepts related to unity and division within groups or communities

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

togetherness or agreement

np_acts-logits-general · gemini-2.0-flash

unity and togetherness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

entibus

-0.42

chieht

-0.42

Бахар

-0.40

clearpage

-0.40

Попис

-0.40

 Wicidata

-0.38

 invokingState

-0.38

inflate

-0.38

 TextInputType

-0.38

äfts

-0.38

POSITIVE LOGITS

 unity

0.88

 united

0.72

unity

0.72

 uniting

0.71

 Unity

0.70

 cohesion

0.70

 unite

0.68

Unity

0.66

 divisive

0.65

 unifying

0.65

Activations Density 0.342%

concepts related to unity and division within groups or communities

togetherness or agreement

unity and togetherness

No Comments

No Known Activations