INDEX

Explanations

references to data sources or origins

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 pleaſure

-0.90

 ſche

-0.88

 ſta

-0.75

 ſtate

-0.74

 juſ

-0.74

 ſol

-0.72

 purpoſe

-0.72

 ſever

-0.71

 myſelf

-0.70

 faſt

-0.70

POSITIVE LOGITS

 from

1.54

from

1.45

 FROM

1.39

 From

1.38

From

1.35

FROM

1.26

getFrom

1.07

จาก

1.05

 dari

0.99

 från

0.97

Activations Density 0.375%

references to data sources or origins

No Comments

No Known Activations