INDEX

Explanations

expressions of possession and experiences related to personal achievements or relationships

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

"ve" or "got" followed by another verb

np_acts-logits-general · gemini-2.0-flash

got, been, or 's followed by got

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

تقاوى

-0.59

abestanden

-0.56

Fns

-0.53

 مرئيه

-0.52

Erstellt

-0.51

RenderAtEndOf

-0.51

///</

-0.51

ScopeManager

-0.51

OGND

-0.49

Happ

-0.49

POSITIVE LOGITS

got

2.70

got

2.30

Got

2.11

Got

2.05

GOT

1.80

GOT

1.50

 gotcha

1.10

 gott

1.09

 gota

1.09

gota

1.07

Activations Density 0.183%

expressions of possession and experiences related to personal achievements or relationships

"ve" or "got" followed by another verb

got, been, or 's followed by got

No Comments

No Known Activations