INDEX

Explanations

acknowledgments and references in academic writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Dr

-0.63

Mr

-0.63

Mrs

-0.62

Dr

-0.58

Ms

-0.58

Mr

-0.56

 Coach

-0.55

 Madam

-0.54

 Driver

-0.53

Mrs

-0.52

POSITIVE LOGITS

帖最后由

0.81

 متعلقه

0.75

 autorytatywna

0.75

 colleagues

0.71

 تانيه

0.71

 дописавши

0.71

 kasarigan

0.69

 دیکھیے

0.68

tagHelperRunner

0.67

,:),

0.67

Activations Density 0.173%

acknowledgments and references in academic writing

No Comments

No Known Activations