INDEX

Explanations

phrases related to contributions and participation in various activities or processes

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

новниш

-0.57

-0.55

 termica

-0.52

SharedDtor

-0.52

 losers

-0.52

はじめに

-0.51

MENAFN

-0.51

bilden

-0.50

 Préférences

-0.50

NavController

-0.50

POSITIVE LOGITS

 contribution

0.94

 contributions

0.90

 contributing

0.86

 contributed

0.84

 contribute

0.83

 contributes

0.78

 Contributions

0.77

 Contribution

0.76

Contribution

0.76

Contributions

0.74

Activations Density 0.523%

phrases related to contributions and participation in various activities or processes

No Comments

No Known Activations