INDEX

Explanations

repetitive use of the word "because."

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

 nadzieję

-0.75

 Shand

-0.75

MigrationBuilder

-0.75

aquin

-0.73

 Lockheed

-0.70

MutableLiveData

-0.69

Jen

-0.69

 Kalman

-0.68

 Menschheit

-0.67

styleUrls

-0.67

POSITIVE LOGITS

Because

1.78

 Because

1.68

because

1.65

 BECAUSE

1.65

 because

1.56

ECAUSE

1.49

Cuz

1.35

 porque

1.32

 Porque

1.31

Cuz

1.26

Activations Density 0.109%

repetitive use of the word "because."

No Comments

No Known Activations