INDEX

Explanations

code-related keywords and function signatures relevant to JavaScript and JNI

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

C/C++ code syntax

np_acts-logits-general · gemini-2.0-flash

native code constructs

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OrEqualTo

-0.46

strup

-0.44

 zbior

-0.43

 drill

-0.43

matchCondition

-0.42

omycin

-0.42

Bronnen

-0.41

PVC

-0.41

żo

-0.41

ieg

-0.40

POSITIVE LOGITS

 native

1.01

native

0.93

 gynhyrchwyd

0.92

 intptr

0.84

 nativo

0.84

Native

0.83

 Native

0.78

 autorytatywna

0.74

 Mérimée

0.73

 nativa

0.72

Activations Density 0.630%

code-related keywords and function signatures relevant to JavaScript and JNI

C/C++ code syntax

native code constructs

No Comments

No Known Activations