INDEX

Explanations

references to movement and change in orientation

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

movement or state change

np_acts-logits-general · gemini-2.0-flash

movement between states

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

łaszcza

-0.55

MessageOf

-0.54

 Vordergrund

-0.52

retts

-0.52

Inhalte

-0.51

 innehå

-0.50

 Awak

-0.49

부터

-0.48

droid

-0.48

навли

-0.48

POSITIVE LOGITS

 depending

0.95

depending

0.85

 dependiendo

0.71

abestanden

0.65

 autorytatywna

0.64

AddTagHelper

0.63

 ujednoznacz

0.57

tanleria

0.56

 Depending

0.55

toggleClass

0.55

Activations Density 0.535%

references to movement and change in orientation

movement or state change

movement between states

No Comments

No Known Activations