INDEX

Explanations

references to items or rewards within a gaming context

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

Comments or text after usernames

np_acts-logits-general · gemini-2.0-flash

game drops and upgrades

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

DoubleQuotes

-0.52

 scrimmage

-0.52

ThroughAttribute

-0.49

,:);

-0.49

 Compton

-0.48

 Spass

-0.46

BeginContext

-0.46

Spots

-0.45

的目光

-0.45

 Keil

-0.44

POSITIVE LOGITS

 autorytatywna

0.79

MigrationBuilder

0.78

AndEndTag

0.72

 CreateTagHelper

0.69

malink

0.62

Rujuakan

0.60

日閲覧

0.59

 newBuilder

0.58

 ProtoMessage

0.57

 للاسماء

0.55

Activations Density 0.057%

references to items or rewards within a gaming context

Comments or text after usernames

game drops and upgrades

No Comments

No Known Activations