INDEX

Explanations

HTML tags and formatting elements across the document

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

HTML list or table formatting tags

np_acts-logits-general · gemini-2.0-flash

HTML tags and lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 autorytatywna

-1.09

 "..\..\..\

-0.81

 "..\..\

-0.81

 يتيمه

-0.78

MLLoader

-0.78

Personendaten

-0.76

ConstraintMaker

-0.74

GEBURTSDATUM

-0.73

 betweenstory

-0.72

 ویکی‌پدیا

-0.71

POSITIVE LOGITS

br

0.74

table

0.63

hr

0.59

br

0.57

ol

0.56

 table

0.54

BR

0.53

0.52

orderList

0.52

0.51

Activations Density 0.441%

HTML tags and formatting elements across the document

HTML list or table formatting tags

HTML tags and lists

No Comments

No Known Activations