INDEX

Explanations

frequent uses of the word "the" in various contexts

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

Follows "the" or "The"

np_acts-logits-general · gemini-2.0-flash

the followed by capitalized entity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 nakalista

-0.79

 بيها

-0.74

ंदीखरीदारी

-0.74

 propOrder

-0.70

 Wicidata

-0.67

 Désolé

-0.64

CTO

-0.63

rungsseite

-0.63

setupUi

-0.61

 سكانية

-0.61

POSITIVE LOGITS

"]];

0.62

Климат

0.53

 unknownFields

0.51

AndroidJUnit

0.48

"]]

0.47

"])){

0.47

']);

0.46

avadoc

0.45

The

0.44

XmlAccessorType

0.44

Activations Density 0.358%

frequent uses of the word "the" in various contexts

Follows "the" or "The"

the followed by capitalized entity

No Comments

No Known Activations