INDEX

Explanations

elements related to software dependencies and configurations

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

Properties or values within XML or code snippets

np_acts-logits-general · gemini-2.0-flash

name followed by equals or tag

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

SharedDtor

-0.82

 Савезне

-0.79

expandindo

-0.75

 فريبيس

-0.72

GEBURTSDATUM

-0.71

Selfer

-0.71

DockStyle

-0.70

errHandler

-0.70

Parcelize

-0.69

ьаж

-0.68

POSITIVE LOGITS

“

0.33

‘

0.32

 colspan

0.31

 vitro

0.30

<blockquote>

0.30

AndWait

0.30

‍♂️

0.30

lowing

0.29

IfNot

0.28

eryl

0.28

Activations Density 0.162%

elements related to software dependencies and configurations

Properties or values within XML or code snippets

name followed by equals or tag

No Comments

No Known Activations