INDEX

Explanations

technical terms and coding-related elements

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

Mathematical or programming notation

np_acts-logits-general · gemini-2.0-flash

HTML tag helpers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

}`)

-0.51

pegno

-0.47

contentLoaded

-0.47

ltä

-0.47

Datagram

-0.47

"}"

-0.46

homonymie

-0.44

ROIT

-0.44

 disagree

-0.44

'")

-0.44

POSITIVE LOGITS

 CURIAM

0.65

WriteTagHelper

0.63

LabelTagHelper

0.63

Kjelder

0.62

Datuak

0.61

stateProvider

0.60

TagMode

0.58

 JAXBElement

0.57

KommentareTeilen

0.57

MLLoader

0.56

Activations Density 0.487%

technical terms and coding-related elements

Mathematical or programming notation

HTML tag helpers

No Comments

No Known Activations