INDEX

Explanations

sequences of numbers and their variations or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 témoig

-0.84

 Waſſer

-0.81

 wiſſen

-0.80

 unſer

-0.79

 zwiſchen

-0.79

 zuſammen

-0.78

ſſung

-0.77

 ſei

-0.77

IntoConstraints

-0.77

 ſein

-0.76

POSITIVE LOGITS

0.35

0.34

My

0.33

and

0.32

My

0.31

Activations Density 0.484%

sequences of numbers and their variations or related terms

No Comments

No Known Activations