INDEX

Explanations

expressions related to data presentation and formatting

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

Code or numerical values

np_acts-logits-general · gemini-2.0-flash

code and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

æring

-0.32

 Partagez

-0.31

 Nación

-0.30

 karşılaş

-0.30

lassung

-0.29

 Utilisez

-0.29

 Leidenschaft

-0.29

jména

-0.29

ドゥ

-0.29

ñado

-0.29

POSITIVE LOGITS

WithIOException

0.88

ValueStyle

0.84

 betweenstory

0.77

verifyException

0.75

 wireType

0.71

 kasarigan

0.71

queryInterface

0.70

 Autorisations

0.70

AndEndTag

0.69

SharedDtor

0.69

Activations Density 2.427%

expressions related to data presentation and formatting

Code or numerical values

code and data structures

No Comments

No Known Activations