INDEX

Explanations

programming-related syntax for data transformations

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

data transformation functions

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

IntoConstraints

-0.56

drawSprites

-0.53

 faſt

-0.50

 AssemblyCulture

-0.48

Autoritní

-0.48

 Gegenteil

-0.47

neſs

-0.46

 Normdatei

-0.44

 betweenstory

-0.44

!\!\

-0.44

POSITIVE LOGITS

TagMode

0.57

yntaxException

0.49

Rhestr

0.43

SuccessListener

0.41

tph

0.40

 déclar

0.39

featureID

0.39

Cubit

0.38

 المعيارى

0.38

 lighten

0.37

Activations Density 0.008%

programming-related syntax for data transformations

data transformation functions

No Comments

No Known Activations