INDEX

Explanations

specific numerical data or references related to studies or documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 ISNI

-0.63

 numerus

-0.62

 useDispatch

-0.61

kloped

-0.60

بوابة

-0.59

 configurer

-0.58

AsUp

-0.57

 fréquent

-0.57

__*/

-0.56

 виправивши

-0.53

POSITIVE LOGITS

 document

0.85

 documents

0.82

documents

0.73

 documento

0.70

 Document

0.69

document

0.67

 drafted

0.66

pdf

0.65

 worksheet

0.65

 sheets

0.65

Activations Density 0.680%

specific numerical data or references related to studies or documents

No Comments

No Known Activations