INDEX

Explanations

elements related to data processing and configuration in a programming context

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

Class or function names

np_acts-logits-general · gemini-2.0-flash

technical components and factory patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

istoitu

-0.45

bootstrapcdn

-0.44

UnitTesting

-0.43

 encontraban

-0.42

ptest

-0.41

Personensuche

-0.41

MemoryWarning

-0.41

 judiciales

-0.41

SaveChangesAsync

-0.40

 drawn

-0.40

POSITIVE LOGITS

 Factory

1.17

 factory

1.14

Factory

1.10

 FACTORY

1.02

 builder

1.00

factory

0.99

 provider

0.96

 Provider

0.94

 Builder

0.94

FACTORY

0.92

Activations Density 0.582%

elements related to data processing and configuration in a programming context

Class or function names

technical components and factory patterns

No Comments

No Known Activations