INDEX

Explanations

code-related terms and references to software libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 NgModule

-0.52

 كورة

-0.50

 Simult

-0.47

Abitanti

-0.47

DrawerToggle

-0.47

 "..\..\..\

-0.47

XmlSchema

-0.46

 aisles

-0.45

parsedMessage

-0.45

 AppCompatTheme

-0.44

POSITIVE LOGITS

MigrationBuilder

0.76

RegressionTest

0.74

 الرياضيه

0.64

دانشنامهٔ

0.63

ModelAdmin

0.57



0.57

BagConstraints

0.55

ttemberg

0.55

 nhiên

0.55

addPreferredGap

0.55

Activations Density 0.142%

code-related terms and references to software libraries

No Comments

No Known Activations