INDEX

Explanations

phrases related to pairwise comparisons and analyses

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

SharedCtor

-0.92

 للاسماء

-0.78

 متعلقه

-0.70

 Référence

-0.67

 autorytatywna

-0.65

 GenerationType

-0.63

 feroit

-0.63

 الحره

-0.62

談社

-0.62

 pères

-0.61

POSITIVE LOGITS

 pairs

0.89

 Pairs

0.81

Pairs

0.80

 Pair

0.74

 paire

0.74

pairs

0.71

Partners

0.71

 pair

0.69

 partners

0.68

 PAIR

0.66

Activations Density 0.127%

phrases related to pairwise comparisons and analyses

No Comments

No Known Activations