INDEX

Explanations

structures and formatting related to programming or coding syntax

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

LaTeX code or mathematical expressions

np_acts-logits-general · gemini-2.0-flash

statistical alignment

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AsUp

-1.12

kloped

-0.87

migrationBuilder

-0.82

Datuak

-0.82

 "..\..\..\

-0.81

 snippetHide

-0.81

WithIOException

-0.81

NUMX

-0.79

XmlAccessType

-0.76

oredCriteria

-0.76

POSITIVE LOGITS

 Absch

0.50

 dommages

0.49

InvalidProtocol

0.45

 jinak

0.44

end

0.43

 falsa

0.42

itemize

0.42

User

0.42

enumerate

0.41

 falsas

0.39

Activations Density 0.017%

structures and formatting related to programming or coding syntax

LaTeX code or mathematical expressions

statistical alignment

No Comments

No Known Activations