INDEX

Explanations

code structure and language constructs related to interfaces and callbacks in programming

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

anonymous methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 AssemblyVersion

-0.62

KommentareTeilen

-0.57

OGND

-0.54

GraphicsUnit

-0.52

 Taktlose

-0.51

routeProvider

-0.49

principalColumn

-0.47

GenerationType

-0.47

'{@

-0.46

 pinulongan

-0.46

POSITIVE LOGITS

 anonymous

0.73

 Anonymous

0.68

anonymous

0.66

Anonymous

0.66

 anonyme

0.59

匿名

0.58

 anony

0.54

 anonim

0.54

 anon

0.52

anon

0.50

Activations Density 0.080%

code structure and language constructs related to interfaces and callbacks in programming

anonymous methods

No Comments

No Known Activations