INDEX

Explanations

elements related to images, templates, and screenshots in the content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 noDo

-0.59

 Taktlose

-0.57

 ब्रेकडाउन

-0.56

GEBURTSDATUM

-0.56

 ſta

-0.54

səhifə

-0.54

 autorytatywna

-0.51

 faſt

-0.50

TagMode

-0.50

 الحره

-0.50

POSITIVE LOGITS

 screenshot

0.48

screen

0.41

 screen

0.41

CppMethod

0.40

ISupport

0.38

screenshot

0.38

autés

0.38

 Confusion

0.37

 Confused

0.37

écran

0.36

Activations Density 0.027%

elements related to images, templates, and screenshots in the content

No Comments

No Known Activations