INDEX

Explanations

references to military operations and units during wartime

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Hozzáférés

-0.70

 MainAxisSize

-0.65



-0.64

ⓘ

-0.62

 CGSize

-0.61

/**

-0.60

__*/

-0.58

 createState

-0.58

Fee

-0.58

Архівовано

-0.57

POSITIVE LOGITS

 wartime

0.68

 Batalla

0.57

 kasarigan

0.52

war

0.51

 gradova

0.50

igshid

0.50

CrossRef

0.49

 WWII

0.49

 виправивши

0.48

parsedMessage

0.47

Activations Density 0.272%

references to military operations and units during wartime

No Comments

No Known Activations