INDEX

Explanations

error messages and exceptions in code

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

Code and mathematical notations

np_acts-logits-general · gemini-2.0-flash

programming keywords and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Biôgrafia

-0.71

 Administrativna

-0.70

IsMutable

-0.68

setVerticalGroup

-0.67

GOTREF

-0.66

Bibliograf

-0.66

 betweenstory

-0.65

SharedDtor

-0.64

IonicModule

-0.63

ardless

-0.61

POSITIVE LOGITS

 isolé

0.47

BackStack

0.46

 isolato

0.46

 Grüsse

0.44

getMessage

0.44

closePath

0.43

BindingResult

0.43

FileDescriptor

0.43

 skul

0.42

 pathology

0.42

Activations Density 0.032%

error messages and exceptions in code

Code and mathematical notations

programming keywords and identifiers

No Comments

No Known Activations