INDEX

Explanations

references to mice and rats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 ویکی‌پدی

-0.76

-0.68

 kasarigan

-0.67

/***/

-0.55

="@+

-0.51

 thăng

-0.50

šana

-0.50

illoma

-0.49

іга

-0.48

bardier

-0.48

POSITIVE LOGITS

 mouse

1.02

 Mouse

1.02

 Mice

0.98

 mice

0.98

mouse

0.97

 rodents

0.95

 MOUSE

0.94

🐁

0.90

🐭

0.88

 rodent

0.87

Activations Density 0.183%

references to mice and rats

No Comments

No Known Activations