INDEX

Explanations

references to code annotations and imports in programming contexts

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

dependency injection and imports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

transQ

-0.46

 jspb

-0.44

googleapis

-0.41

 doccia

-0.41

ofür

-0.40

tamol

-0.40

cipar

-0.39

що

-0.39

PHPExcel

-0.38

apimachinery

-0.38

POSITIVE LOGITS

MockBean

0.77

Resource

0.57

CppMethod

0.56

 Resource

0.56

 autorytatywna

0.53

 propOrder

0.53

 getResource

0.52

ViewChild

0.52

 RESOURCE

0.51

WriteBarrier

0.50

Activations Density 0.000%

references to code annotations and imports in programming contexts

dependency injection and imports

No Comments

No Known Activations