INDEX

Explanations

occurrences of the pronoun "me."

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

"me"

np_acts-logits-general · gemini-2.0-flash

me followed by verbs

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

leſs

-0.48

shadowOffset

-0.46

 vín

-0.45

 auroit

-0.41

 vytvoř

-0.40

setOpen

-0.40

capan

-0.40

"",

-0.40

 flott

-0.39

 éter

-0.39

POSITIVE LOGITS

me

1.67

Me

1.35

Me

1.29

me

1.19

ME

1.12

ME

1.02

 мной

0.77

 Mejía

0.75

我

0.73

Meik

0.72

Activations Density 0.052%

occurrences of the pronoun "me."

"me"

me followed by verbs

No Comments

No Known Activations