INDEX

Explanations

references to maps and their related features or representations

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

Diagrams, maps, and representations

np_acts-logits-general · gemini-2.0-flash

maps, diagrams, schemes, plans

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-------

-0.57

ExecuteReader

-0.54

 robar

-0.52

 autorytatywna

-0.51

 informée

-0.50

 iconTwitter

-0.49

iastes

-0.47

 recours

-0.46

 citoy

-0.46

 ekor

-0.44

POSITIVE LOGITS

 diagram

0.68

 diagrams

0.67

 Diagram

0.59

 maps

0.59

 Diagrams

0.58

Diagram

0.57

adaptiveStyles

0.55

map

0.55

diagram

0.54

 schematic

0.53

Activations Density 0.591%

references to maps and their related features or representations

Diagrams, maps, and representations

maps, diagrams, schemes, plans

No Comments

No Known Activations