INDEX

Explanations

references to glitches or issues in games

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

Following tokens such as "cuz", "so", or a comma

np_acts-logits-general · gemini-2.0-flash

informal language and questions

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

rungsseite

-0.88

sizeCache

-0.86

__":

-0.82

DataAnnotations

-0.82

XmlAccessType

-0.81

 الحره

-0.77

DockStyle

-0.73

Tikang

-0.71

Folks

-0.71

DeleteBehavior

-0.71

POSITIVE LOGITS

 roblox

0.64

 perciò

0.63

 sortes

0.62

idk

0.60

 skolan

0.60

;-;

0.59

 Roblox

0.58

 maioria

0.58

sphase

0.56

 victimes

0.55

Activations Density 0.702%

references to glitches or issues in games

Following tokens such as "cuz", "so", or a comma

informal language and questions

No Comments

No Known Activations