INDEX

Explanations

phrases indicating frequency or repetition

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

Word "times" and its variants

np_acts-logits-general · gemini-2.0-flash

times

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

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

IntoConstraints

-0.55

SBATCH

-0.42

SafeAreaView

-0.41

出一

-0.38

uio

-0.36

 minY

-0.36

 lieu

-0.35

Guidance

-0.34

guidance

-0.33

CFG

-0.33

POSITIVE LOGITS

 times

1.28

 TIMES

1.20

Times

1.17

twice

1.16

Twice

1.16

 twice

1.14

 Times

1.13

times

1.13

 Twice

1.10

 veces

1.08

Activations Density 0.228%

phrases indicating frequency or repetition

Word "times" and its variants

times

No Comments

No Known Activations