INDEX

Explanations

programming constructs related to function definitions and return statements

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

Less than or equal to operator

np_acts-logits-general · gemini-2.0-flash

code and mathematical expressions

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

 oficio

-0.38

 elä

-0.37

 udě

-0.37

 hombro

-0.36

 cuchillo

-0.36

 delgada

-0.35

 aclarar

-0.34

 hacerte

-0.33

 juuri

-0.33

 tapaht

-0.33

POSITIVE LOGITS

our

0.57

🏻

0.54

 MainActivity

0.52

::$_

0.52

GeoNames

0.52

SqlClient

0.52

execSQL

0.51

 ब्रेकडाउन

0.51

🏼

0.51

mmt

0.50

Activations Density 0.863%

programming constructs related to function definitions and return statements

Less than or equal to operator

code and mathematical expressions

No Comments

No Known Activations