INDEX

Explanations

function calls related to converting views in programming

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

technical documentation and code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

expandindo

-0.70

MigrationBuilder

-0.65

 ExecuteAsync

-0.65

queryInterface

-0.60

ChildScrollView

-0.60

лтемелер

-0.60

 GenerationType

-0.58

autorest

-0.58

BeginContext

-0.58

oa̍t

-0.57

POSITIVE LOGITS

SourceChecksum

0.39

TagHelper

0.38

usch

0.38

 NSCoder

0.37

CodeAttribute

0.34

şen

0.34

 ausgest

0.33

makeConstraints

0.33

 Mature

0.31

Inflater

0.31

Activations Density 0.000%

function calls related to converting views in programming

technical documentation and code

No Comments

No Known Activations