INDEX

Explanations

technical keywords and function definitions related to programming, particularly focused on Java, JavaScript, and JNI (Java Native Interface)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

="@+

-0.50

inola

-0.49

 Sena

-0.48

omycin

-0.47

 zbior

-0.46

 Fleur

-0.45

urger

-0.45

 baker

-0.44

amycin

-0.44

transQ

-0.43

POSITIVE LOGITS

 native

0.91

native

0.85

 Native

0.83

Native

0.83

JNI

0.82

JNI

0.77

JNIEnv

0.77

 IntPtr

0.75

IntPtr

0.74

 natives

0.73

Activations Density 0.819%

technical keywords and function definitions related to programming, particularly focused on Java, JavaScript, and JNI (Java Native Interface)

No Comments

No Known Activations