INDEX

Explanations

programming constructs, specifically focusing on loop structures

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

Code snippets with loop indices

np_acts-logits-general · gemini-2.0-flash

lists and arrays

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 виправивши

-0.72

ViewFeatures

-0.70



-0.62

MigrationBuilder

-0.59

xtext

-0.56

SequentialGroup

-0.55

 препратки

-0.54

 BrowserModule

-0.54

 متعلقه

-0.53

titleMargin

-0.53

POSITIVE LOGITS

AsUp

0.63

SerializeField

0.60

stopPropagation

0.56

inventory

0.56

 alphabetically

0.55

عدد

0.52

 Roster

0.51

Reklama

0.48

 đàn

0.47

 Kanz

0.47

Activations Density 0.060%

programming constructs, specifically focusing on loop structures

Code snippets with loop indices

lists and arrays

No Comments

No Known Activations