INDEX

Explanations

mathematical terms and symbols related to equations and theorems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

सन्दर्भ

-0.95

 onPostExecute

-0.89

 فريبيس

-0.82

 Kade

-0.81

 mellitus

-0.78

 Lindgren

-0.78

 Nilsson

-0.74

Παραπομπές

-0.74

 Pohl

-0.73

<^

-0.72

POSITIVE LOGITS

mrow

2.59

клопе

0.65

 Brus

0.64

numerusform

0.63

]{\

0.62

Gek

0.60

featureID

0.60

 Jeremiah

0.59

thenia

0.59

`{

0.59

Activations Density 0.059%

mathematical terms and symbols related to equations and theorems

No Comments

No Known Activations