INDEX

Explanations

specific symbols and formatting in scientific notation or identifiers

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

Superscripted numbers

np_acts-logits-general · gemini-2.0-flash

mathematical notation and symbols

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

.*")]

-0.66

ConstraintMaker

-0.56

+:+

-0.53

transQ

-0.53

fromnode

-0.46

 betweenstory

-0.45

ItemBackground

-0.45

richTextPanel

-0.39

 Driscoll

-0.39

 connections

-0.38

POSITIVE LOGITS

 autorytatywna

0.77

 surla

0.57

 Италијани

0.56

 كومونز

0.54

tagext

0.54

 ब्रेकडाउन

0.52

ⓧ

0.52

хьтан

0.51

FormTagHelper

0.50

 Inſ

0.49

Activations Density 0.702%

specific symbols and formatting in scientific notation or identifiers

Superscripted numbers

mathematical notation and symbols

No Comments

No Known Activations