INDEX

Explanations

programming-related syntax and keywords

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

<start_of_turn> user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 فريبيس

-0.72

 StringTokenizer

-0.66

تقاوى

-0.65

 CreateTagHelper

-0.60

DrawerToggle

-0.60

 للمعارف

-0.60

 دیکھیے

-0.59

 utafitiHapana

-0.59

ArgsConstructor

-0.57

DoubleQuotes

-0.57

POSITIVE LOGITS

primaryStage

0.33

 жур

0.32

 terminal

0.31

isfile

0.30

ProcessEvent

0.30

law

0.29

SaveChangesAsync

0.29

`.

0.28

 messe

0.28

^=

0.28

Activations Density 0.000%

programming-related syntax and keywords

<start_of_turn> user

No Comments

No Known Activations