INDEX

Explanations

connective words or conjunctions in text

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

"and" (possibly questions)

np_acts-logits-general · gemini-2.0-flash

and or

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

RegressionTest

-0.74

GEBURTSDATUM

-0.64

 disambiguazione

-0.63

Personensuche

-0.57

 Wikimedijinoj

-0.51

PreferredItem

-0.48

DIPSETTING

-0.47

mtrl

-0.45

tagHelperRunner

-0.45

+#+#

-0.45

POSITIVE LOGITS

0.45

 einstellen

0.39

Legături

0.38

drücken

0.37

źródło

0.36

 interesantes

0.36

levance

0.35

kozá

0.34

 Bedien

0.34

 možnosti

0.34

Activations Density 0.544%

connective words or conjunctions in text

"and" (possibly questions)

and or

No Comments

No Known Activations