INDEX

Explanations

mathematical expressions and relationships related to probabilistic models and their interpretations

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

Verbs that quantify or describe

np_acts-logits-general · gemini-2.0-flash

describes or quantifies relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Roskov

-0.50

 pegatinas

-0.49

 mijne

-0.48

 kvä

-0.47

 lecciones

-0.46

 arkiv

-0.43

 privada

-0.43

 zelve

-0.43

 виправивши

-0.43

 Вікі

-0.43

POSITIVE LOGITS

 AssemblyCompany

0.51

 essentially

0.44

 Essentially

0.43

 basically

0.42

essentially

0.42

 represent

0.41

ReusableCell

0.41

__":

0.40

basically

0.40

 gynhyrchwyd

0.40

Activations Density 1.167%

mathematical expressions and relationships related to probabilistic models and their interpretations

Verbs that quantify or describe

describes or quantifies relationships

No Comments

No Known Activations