INDEX

Explanations

instances of the word "awarded" and related terms indicating recognition or honors given to individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 المعيارى

-0.88

LookAnd

-0.73

czegó

-0.67

脚注の使い方

-0.66

íncia

-0.66

NOPQRST

-0.64

 uParam

-0.61

setLayoutManager

-0.61

ukone

-0.59

kuuta

-0.59

POSITIVE LOGITS

 awarded

2.19

 Awarded

1.73

 awarding

1.51

 granted

1.29

granted

1.06

 rewarded

1.03

 conferred

0.95

 Granted

0.89

 granting

0.89

 accorded

0.83

Activations Density 0.255%

instances of the word "awarded" and related terms indicating recognition or honors given to individuals or entities

No Comments

No Known Activations