INDEX

Explanations

details related to diet and food preferences

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

 alcohol

-0.67

 cognac

-0.65

coffee

-0.63

 Kopi

-0.63

 whiskey

-0.62

Alcohol

-0.62

 whisky

-0.61

AddTagHelper

-0.60

 coffee

-0.60

alcoholic

-0.60

POSITIVE LOGITS

 carrots

0.89

 Carrots

0.87

 cabbage

0.85

 vegetables

0.82

 carrot

0.80

 vegetable

0.80

 turnips

0.80

 Cabbage

0.79

 greens

0.78

 Carrot

0.76

Activations Density 0.291%

details related to diet and food preferences

No Comments

No Known Activations