INDEX

Explanations

terms related to "pre-" prefixes or pre-scheduled events and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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



-0.92

(@"%@",

-0.85

 Wallflower

-0.85

KommentareTeilen

-0.84

bolista

-0.83

 دیکھیے

-0.83

}{*}{}

-0.83

 Gazetteer

-0.81

 CiNii

-0.81

 Wikispecies

-0.80

POSITIVE LOGITS

Pre

1.65

PRE

1.58

PRE

1.55

Pre

1.52

pre

1.39

pre

1.36

 pré

1.14

 Pref

1.10

 Pré

1.08

PreExecute

1.06

Activations Density 0.147%

terms related to "pre-" prefixes or pre-scheduled events and actions

No Comments

No Known Activations