INDEX

Explanations

code-related structures, specifically class definitions and related annotations

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

Code, Java, or Class-related terms

np_acts-logits-general · gemini-2.0-flash

Java class and method names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

homonymie

-0.53

 ujednoznacz

-0.51

nP

-0.48

arXiv

-0.48

retas

-0.45

EXTERN

-0.45

✭✭

-0.44

वाह

-0.43

脚

-0.42

styleUrls

-0.41

POSITIVE LOGITS

Personensuche

0.68

AccessFile

0.65

jdk

0.65

JDK

0.65

JVM

0.63

JVM

0.63

 Java

0.62

 Numerade

0.61

JDK

0.61

sun

0.60

Activations Density 0.439%

code-related structures, specifically class definitions and related annotations

Code, Java, or Class-related terms

Java class and method names

No Comments

No Known Activations