INDEX

Explanations

terms related to data structure and manipulation in programming contexts

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

Code or markup with associated data/values

np_acts-logits-general · gemini-2.0-flash

sporadic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

+#+

-0.85

ThroughAttribute

-0.81

 ExecuteAsync

-0.72

 Administrativna

-0.71

 незавершена

-0.70

 esternos

-0.67

 الرياضيه

-0.65

Geplaatst

-0.64

PerformLayout

-0.60

évaluateur

-0.60

POSITIVE LOGITS

MessageTagHelper

0.41

 Hauteur

0.31

Ventajas

0.31

 Wesen

0.31

反應

0.31

SharedCtor

0.30

重启

0.29

 Ursprung

0.29

搭載

0.28

 Reaktion

0.28

Activations Density 1.167%

terms related to data structure and manipulation in programming contexts

Code or markup with associated data/values

sporadic

No Comments

No Known Activations