INDEX

Explanations

components of personal names and titles

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

This image

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ChildScrollView

-0.60

Rptr

-0.48

AsUp

-0.47

formik

-0.45

Transcripción

-0.45

quelize

-0.45

daging

-0.45

queryInterface

-0.43

]")]

-0.43

 Infórmanos

-0.42

POSITIVE LOGITS

 CreateTagHelper

0.45

ьажоргаш

0.42

richTextPanel

0.41

 István

0.41

XmlRootElement

0.41

}]);

0.40

 jScrollPane

0.40

rawDesc

0.39

notice

0.39

ęb

0.37

Activations Density 0.060%

components of personal names and titles

This image

No Comments

No Known Activations