INDEX

Explanations

references to variables and methods within programming contexts

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

code definitions and declarations

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

GraphicsUnit

-0.83

ɵɵ

-0.70

migrationBuilder

-0.69

 Italijanski

-0.66

/\.

-0.65

oredCriteria

-0.65

OGND

-0.64

yarnpkg

-0.63

principalColumn

-0.63

 referrerpolicy

-0.62

POSITIVE LOGITS

 variables

0.35

 matters

0.35

 extérieur

0.34

zeichnungen

0.30

elernt

0.30

 redacción

0.30

 here

0.30

 aspects

0.29

 elements

0.29

 provisoire

0.29

Activations Density 0.012%

references to variables and methods within programming contexts

code definitions and declarations

No Comments

No Known Activations