INDEX

Explanations

programming structures and syntax related to loops and iterations in code

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 @ 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

ніципалі

-0.57

 <=",

-0.49

hasiswa

-0.46

 Serif

-0.46

styleType

-0.44

CppMethod

-0.43

ports

-0.42

 للاسماء

-0.42

QtWidgets

-0.41

 Opti

-0.41

POSITIVE LOGITS

WebElementEntity

0.36

PreInfinity

0.36

violi

0.35

MigrationBuilder

0.35

AutoModerator

0.35

amblea

0.35

 سكانية

0.35

 Herodotus

0.34

 Popis

0.32

Koordinaten

0.32

Activations Density 0.006%

programming structures and syntax related to loops and iterations in code

<start_of_turn> user

No Comments

No Known Activations