INDEX

Explanations

elements related to mathematical notation and variables in statistical contexts

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

Mathematical notation: subscripts and superscripts

np_acts-logits-general · gemini-2.0-flash

variable assignment. special characters followed by indices

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

-0.83

SharedCtor

-0.76

 الحره

-0.76

 insuffisamment

-0.74

">//

-0.72

AccessorTable

-0.72

 للاسماء

-0.68

expandindo

-0.66

]='\

-0.64

TestingModule

-0.64

POSITIVE LOGITS

0.47

msgTypes

0.46

ligkeit

0.41

codegen

0.41

sscanf

0.40

ویه

0.39

 składa

0.39

baba

0.39

🛸

0.39

SBATCH

0.38

Activations Density 1.112%

elements related to mathematical notation and variables in statistical contexts

Mathematical notation: subscripts and superscripts

variable assignment. special characters followed by indices

No Comments

No Known Activations