INDEX

Explanations

terms related to environmental policies and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

TagMode

-0.74

AddTagHelper

-0.70

 AssemblyCulture

-0.70

 Nigerian

-0.67

ēju

-0.65

 Nigeria

-0.64

hintText

-0.63

 pinulongan

-0.62

ագրություններ

-0.61

 thước

-0.61

POSITIVE LOGITS

NZ

1.48

 Auckland

1.43

NZ

1.40

 Maori

1.35

 Māori

1.32

Auckland

1.32

 Kiwi

1.30

 Christchurch

1.21

Kiwi

1.21

 Otago

1.18

Activations Density 0.206%

terms related to environmental policies and regulations

No Comments

No Known Activations