INDEX

Explanations

terms related to health, nutrition, and dietary practices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

RenderAtEndOf

-0.67

Conf

-0.54

 mandat

-0.54

 Bever

-0.51

 Confessions

-0.50

хьтан

-0.50

 pecuniary

-0.49

atric

-0.49

 episcopal

-0.48

 surveyed

-0.48

POSITIVE LOGITS

 cells

0.93

 nutrients

0.82

 toxins

0.78

 metabo

0.77

 cellular

0.75

 metabolism

0.73

 nutrient

0.72

 Cells

0.71

 enzymes

0.70

 CELLS

0.69

Activations Density 0.310%

terms related to health, nutrition, and dietary practices

No Comments

No Known Activations