INDEX

Explanations

technical or programming-related terms and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

出版年

-0.59

DialogContent

-0.49

#+#

-0.46

XmlAccessType

-0.46

focusable

-0.45

 Coop

-0.45

 placas

-0.45

createClass

-0.45

 Dann

-0.43

prá

-0.43

POSITIVE LOGITS

AlterField

0.80

StoryboardSegue

0.78

Portail

0.74

Portale

0.71

Bibliograf

0.70

"}";

0.68

 مشين

0.68

 استنادى

0.67

دانشنامهٔ

0.66

ViewFeatures

0.63

Activations Density 0.332%

technical or programming-related terms and specifications

No Comments

No Known Activations