INDEX

Explanations

mathematical symbols and formatting used in equations

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

Text inside of math equations

np_acts-logits-general · gemini-2.0-flash

latex \left delimiters

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

endregion

-0.54

ForUser

-0.51

UrlEncoded

-0.47

 vôtre

-0.46

Océ

-0.42

 MyApp

-0.41

 shall

-0.41

alumno

-0.40

TabControl

-0.39

larna

-0.38

POSITIVE LOGITS

left

0.82

fjspx

0.68

findpost

0.65

makeText

0.60

__(/*!

0.57

 Италијани

0.54

 unſ

0.54



0.53

 disponibilités

0.52

<i>

0.51

Activations Density 1.035%

mathematical symbols and formatting used in equations

Text inside of math equations

latex \left delimiters

No Comments

No Known Activations