INDEX

Explanations

words related to animals, particularly in the context of studies and research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 ujednoznacz

-0.84

 Lupin

-0.79

 كومونز

-0.76

šanās

-0.75

 mediodía

-0.74

 dourada

-0.73

èches

-0.73

 dysplasia

-0.73

 sherds

-0.72

 thrones

-0.72

POSITIVE LOGITS

 animal

1.66

 animals

1.62

 Animal

1.54

Animal

1.46

animal

1.46

animals

1.44

 Animals

1.42

 ANIMAL

1.38

ANIMAL

1.33

Animals

1.33

Activations Density 0.057%

words related to animals, particularly in the context of studies and research

No Comments

No Known Activations