INDEX

Explanations

technical terms associated with programming and data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

$_['

-0.54

իս

-0.54

 lenker

-0.53

 disambiguazione

-0.53

 reflect

-0.52

andola

-0.52

 Angele

-0.51

}$\\

-0.49

Cf

-0.49

 Rine

-0.45

POSITIVE LOGITS

setVerticalGroup

0.82

boots

0.78

UnsafeEnabled

0.77

 boots

0.69

 BOOT

0.68

 booted

0.67

Citiți

0.67

Sequ

0.66

 Normdatei

0.66

 brakes

0.65

Activations Density 2.553%

technical terms associated with programming and data analysis

No Comments

No Known Activations