INDEX

Explanations

references to recognition or acknowledgment 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

rosophila

-0.73

gdx

-0.72

ตร์

-0.72

 allons

-0.71

 frattempo

-0.70

Ous

-0.70

://

-0.70

 âgées

-0.66

ortiment

-0.65

nyv

-0.65

POSITIVE LOGITS

 recogni

1.83

 recognition

1.75

 recognise

1.68

 RECOGN

1.66

 recognised

1.63

 Recognition

1.57

 recognize

1.57

 recognises

1.56

 recognising

1.56

 Recogn

1.51

Activations Density 0.064%

references to recognition or acknowledgment in various contexts

No Comments

No Known Activations