INDEX

Explanations

distinctive traits or qualities associated with specific subjects or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Musique

-0.44

chränk

-0.42

šanai

-0.41

IndentedString

-0.40

Fordítás

-0.40

-0.39

 pères

-0.39

OrderService

-0.39

 pharynx

-0.37

İstinadlar

-0.36

POSITIVE LOGITS

 characteristic

1.37

 Characteristic

1.27

 characteristics

1.23

characteristic

1.19

 Characteristics

1.19

characteristics

1.14

Characteristics

1.09

 caratter

1.07

Characteristic

1.07

 caractéristique

1.03

Activations Density 0.451%

distinctive traits or qualities associated with specific subjects or concepts

No Comments

No Known Activations