INDEX

Explanations

references to variables and their attributes in programming contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 pleno

-0.56

 pestañas

-0.56

 actionMode

-0.54

mulo

-0.53

 autorytatywna

-0.53

ثم

-0.50

 Mero

-0.50

 Доба

-0.50

 shaggy

-0.50

 estekak

-0.50

POSITIVE LOGITS

djangoproject

0.87

 useState

0.79

useState

0.73

 كومونز

0.71

SerializeField

0.65

 useRef

0.65

apunov

0.64

endphp

0.63

apimachinery

0.63

 nahilalakip

0.61

Activations Density 0.426%

references to variables and their attributes in programming contexts

No Known Activations