INDEX

Explanations

references to categories or classifications

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

Code snippets or special characters

np_acts-logits-general · gemini-2.0-flash

multiple languages, dates, programming syntax

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

textColor

-0.49

dorf

-0.45

был

-0.43

WTF

-0.43

нем

-0.42

org

-0.41

mob

-0.41

int

-0.40

enskap

-0.40

bní

-0.39

POSITIVE LOGITS

 дописавши

1.14

 autorytatywna

1.11

IndentedString

1.11

Personensuche

0.99

✨:

0.95

GEBURTSDATUM

0.95

verwijspagina

0.94

InjectAttribute

0.94

expandindo

0.91

 kaarangay

0.91

Activations Density 0.387%

references to categories or classifications

Code snippets or special characters

multiple languages, dates, programming syntax

No Comments

No Known Activations