INDEX

Explanations

notations related to algorithmic complexity and data structures

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

O(N) complexity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 Wicidata

-0.48

 &___

-0.47

//</

-0.43

 виправивши

-0.43

CloseOperation

-0.43

FontOfSize

-0.42

Soto

-0.42

Geplaatst

-0.41

 soto

-0.41

 Curi

-0.41

POSITIVE LOGITS

tagHelperRunner

0.68

تقاوى

0.43

 consultato

0.41

aarrggbb

0.40

 calendriers

0.40

Portale

0.39

 getItemCount

0.39

envolvimento

0.39

 Sebab

0.37

новништво

0.37

Activations Density 0.039%

notations related to algorithmic complexity and data structures

O(N) complexity

No Comments

No Known Activations