INDEX

Explanations

code structure and data manipulation related to functions and classes in programming

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

programming functions

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

 MainAxisSize

-0.54

bootstrapcdn

-0.51

SOUNDBITE

-0.51

AnchorStyles

-0.51

MigrationBuilder

-0.50

словно

-0.44

 estekak

-0.42

SEGUIR

-0.42

ZoneId

-0.41

numerusform

-0.40

POSITIVE LOGITS

 records

0.42

enedor

0.41

Personensuche

0.40

 mostrarán

0.39

OpenHelper

0.39

ValueGenerated

0.38

 demen

0.37

 المعيارى

0.36

irited

0.36

PerPage

0.35

Activations Density 0.010%

code structure and data manipulation related to functions and classes in programming

programming functions

No Comments

No Known Activations