INDEX

Explanations

instances of the word "share" and related terms that indicate sharing or distribution

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

LookAnd

-0.99

 فريبيس

-0.97

ftagPool

-0.72

 Highness

-0.70

CloseOperation

-0.70

出版年

-0.66

 AssemblyProduct

-0.66

부터

-0.65

IndentedString

-0.63

 seguida

-0.63

POSITIVE LOGITS

 shares

0.89

 Shares

0.86

 SHARE

0.85

 Sharing

0.82

Sharing

0.78

 sharing

0.77

 Share

0.75

cropping

0.72

 share

0.72

sharing

0.70

Activations Density 0.070%

instances of the word "share" and related terms that indicate sharing or distribution

No Comments

No Known Activations