INDEX

Explanations

terms related to mathematical or physical concepts in formal writing

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

Mathematical formulas/variables

np_acts-logits-general · gemini-2.0-flash

gauge-invariant terms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

⊆

-0.55

تقاوى

-0.50

 crumb

-0.50

Akt

-0.49

 weißt

-0.48

lceil

-0.48

вер

-0.48

 congruence

-0.47

ाउ

-0.47

digitalWrite

-0.47

POSITIVE LOGITS

SharedCtor

0.91

IntoConstraints

0.79

:✨

0.79

 autorytatywna

0.77

 Lordships

0.66

 spontan

0.65

AxisAlignment

0.65

حياته

0.64

XDECREF

0.64

Hentet

0.63

Activations Density 3.624%

terms related to mathematical or physical concepts in formal writing

Mathematical formulas/variables

gauge-invariant terms

No Comments

No Known Activations