INDEX

Explanations

elements of programming constructs or methods

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

code property access followed by parenthesis

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

CloseOperation

-0.71

 дописавши

-0.55

rawDesc

-0.50

+#+#

-0.49

IBOutlet

-0.46

PickerController

-0.46

ThroughAttribute

-0.44

 تكبرها

-0.44

сылкі

-0.44

PYX

-0.43

POSITIVE LOGITS

 kiệm

0.41

はじめに

0.39

IntoConstraints

0.37

XmlEnum

0.37

 canlynol

0.35

ỡng

0.35

 pesada

0.34

了口气

0.33

TagMode

0.32

Попис

0.32

Activations Density 0.008%

elements of programming constructs or methods

code property access followed by parenthesis

No Comments

No Known Activations