INDEX

Explanations

references to animals and animal-related research or testing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Rhapsody

-0.75

 Lupin

-0.73

Blame

-0.71

 ujednoznacz

-0.71

utenants

-0.70

withstanding

-0.69

 كومونز

-0.69

 pravi

-0.68

Teb

-0.67

 convaincre

-0.67

POSITIVE LOGITS

 animal

1.62

 animals

1.52

 Animal

1.46

Animal

1.38

animal

1.38

animals

1.34

 Animals

1.33

 ANIMAL

1.31

ANIMAL

1.30

Animals

1.29

Activations Density 0.073%

references to animals and animal-related research or testing

No Comments

No Known Activations