INDEX

Explanations

instances of the term "classification" and related classifications 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

-0.91

 économ

-0.72

 épar

-0.71

Etern

-0.71

 Johnnie

-0.69

runApp

-0.69

lehnt

-0.69

enumi

-0.68

 venait

-0.67

 démo

-0.67

POSITIVE LOGITS

 classification

1.34

 classify

1.32

 classified

1.31

 Classi

1.31

 Classified

1.24

 classi

1.21

Classify

1.17

 CLASSIFICATION

1.17

lassification

1.17

 Classification

1.16

Activations Density 0.090%

instances of the term "classification" and related classifications in various contexts

No Comments

No Known Activations