INDEX

Explanations

references to images and their descriptions within a document

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

specific page numbers

np_acts-logits-general · gemini-2.0-flash

on page references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

MemoryWarning

-0.85

 disambiguazione

-0.81

 betweenstory

-0.74

 дописавши

-0.67

Personensuche

-0.66

WebServlet

-0.62

NegativeButton

-0.62

хьтан

-0.58

كويكب

-0.58

 AspNetCore

-0.57

POSITIVE LOGITS

 page

1.67

page

1.46

 pages

1.37

Page

1.36

 Page

1.33

pages

1.25

 PAGE

1.18

PAGE

1.13

 pagina

1.06

 página

1.03

Activations Density 0.244%

references to images and their descriptions within a document

specific page numbers

on page references

No Comments

No Known Activations