INDEX

Explanations

expressions of high regard or positive assessments

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ViewFeatures

-1.03

weile

-0.86

etcode

-0.84

θρώ

-0.81

Geografie

-0.79

Linki

-0.78

transQ

-0.78

umenical

-0.77

Sneaky

-0.77

Demographics

-0.77

POSITIVE LOGITS

 best

2.23

best

2.17

 Best

2.11

 BEST

2.10

Best

2.07

BEST

2.04

melhor

1.33

 meilleur

1.31

 terbaik

1.28

 melhores

1.26

Activations Density 0.046%

expressions of high regard or positive assessments

No Comments

No Known Activations