INDEX

Explanations

gendered references in the text

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

Numbers followed by gendered nouns

np_acts-logits-general · gemini-2.0-flash

linking enumerations and counts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 RoutedEventArgs

-0.51

RTRS

-0.48

klart

-0.47

 localisation

-0.46

toBeTruthy

-0.46

Gizmos

-0.45

posedge

-0.45

WriteTagHelper

-0.44

хьтан

-0.44

obio

-0.44

POSITIVE LOGITS

msgTypes

0.41

 برانيه

0.38

SerializeField

0.35

 елның

0.34

IonicModule

0.34

Aholisi

0.34

 erfü

0.32

BeginContext

0.32

 telefónica

0.32

かわらず

0.31

Activations Density 0.947%

gendered references in the text

Numbers followed by gendered nouns

linking enumerations and counts

No Comments

No Known Activations