INDEX

Explanations

references to personal experiences or perspectives

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

First-person pronouns and possessives

np_acts-logits-general · gemini-2.0-flash

myopia, My Hero Academia

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

CloseOperation

-0.93

 themselves

-0.75

SpringBootTest

-0.75

verwijspagina

-0.72

 irse

-0.71

 kanyang

-0.70

themselves

-0.68

 désolés

-0.67

%");

-0.65

 meille

-0.65

POSITIVE LOGITS

 myself

2.60

myself

1.90

my

1.83

 Myself

1.62

my

1.52

 mijn

1.33

 myſelf

1.32

am

1.25

 خودم

1.21

我的

1.20

Activations Density 1.316%

references to personal experiences or perspectives

First-person pronouns and possessives

myopia, My Hero Academia

No Comments

No Known Activations

references to personal experiences or perspectives

First-person pronouns and possessives

myopia, My Hero Academia

No Comments

No Known Activations