INDEX

Explanations

technical terms and findings related to research methodology

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

–

-0.56

Portale

-0.54

-0.53

 mại

-0.51

 spanish

-0.50

-0.49

 delà

-0.48

 chinese

-0.47

 gonna

-0.47

POSITIVE LOGITS

tvguidetime

0.72

Vidite

0.63

таратура

0.62

 doubtnut

0.61

CAPTION

0.61

 onCreateView

0.59

webElementGuid

0.59

paravant

0.59

verwijspagina

0.58

]]

0.58

Activations Density 0.905%

technical terms and findings related to research methodology

No Comments

No Known Activations