INDEX

Explanations

terms related to breadth or broadness in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 مرئيه

-0.98

 المعيارى

-0.96

 وتسجيلات

-0.87

 Paglinawan

-0.86

saraba

-0.82

 Jaffe

-0.82

 Мексичка

-0.81

 ivelany

-0.78

 Gurney

-0.77

lapsingToolbar

-0.76

POSITIVE LOGITS

aktery

0.88

‚

0.79

 Geor

0.75

0.71

</i>

0.68

océan

0.66

 Judi

0.66

Eben

0.66

 Grizzlies

0.65

</h6>

0.65

Activations Density 0.744%

terms related to breadth or broadness in various contexts

No Comments

No Known Activations