INDEX

Explanations

keywords pertaining to various categories including types of products, scientific terms, and statistical concepts

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

XmlAccessType

-0.56

EditorBrowsable

-0.53

AddHtmlAttribute

-0.49

 nakalista

-0.46

 AssemblyTitle

-0.46

 kasarigan

-0.46

HasAnnotation

-0.45

GraphicsUnit

-0.44

CodeAttribute

-0.44

 gesetz

-0.43

POSITIVE LOGITS

migrationBuilder

0.52

FormTagHelper

0.50

 CURIAM

0.50

exitRule

0.47

rubin

0.45

Tumor

0.43

ItemLayout

0.42

 Verſ

0.41

lesque

0.41

 shayari

0.41

Activations Density 0.207%

keywords pertaining to various categories including types of products, scientific terms, and statistical concepts

No Comments

No Known Activations