INDEX

Explanations

food-related terms and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

RegressionTest

-0.86

 فريبيس

-0.75

SequentialGroup

-0.69

writeField

-0.62

RectangleBorder

-0.61

 autorytatywna

-0.61

ActivityCompat

-0.61

ึกษา

-0.60

 GenerationType

-0.60

illoma

-0.60

POSITIVE LOGITS

 meal

1.19

 food

1.13

 meals

1.12

 cuisine

1.05

 dinner

1.00

 delicious

0.97

food

0.96

 foods

0.94

Food

0.89

 dinners

0.88

Activations Density 0.271%

food-related terms and expressions

No Comments

No Known Activations