INDEX

Explanations

expressions related to mathematical notation and equations

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

LaTeX labels

np_acts-logits-general · gemini-2.0-flash

LaTeX labels

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 https

-0.64

https

-0.60

 COVID

-0.57

eqref

-0.57

 GitHub

-0.53

posedge

-0.53

🧵

-0.52

\_

-0.51

 pris

-0.51

POSITIVE LOGITS

 läßt

0.75

 Moslem

0.73

AnchorStyles

0.73

Rohy

0.73

 employes

0.64

 становника

0.64

 Lordships

0.64

 Préférences

0.63

*/),

0.63



0.59

Activations Density 0.416%

expressions related to mathematical notation and equations

LaTeX labels

LaTeX labels

No Comments

No Known Activations