INDEX

Explanations

phrases related to health communication and understanding

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

Simplified explanations

np_acts-logits-general · gemini-2.0-flash

plain language explanations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

mybatisplus

-0.68

principalColumn

-0.67

पया

-0.55

 noDo

-0.54

UseVisualStyle

-0.52

 vidro

-0.48

httphttps

-0.48

CloseOperation

-0.47

InSection

-0.47

 CascadeType

-0.47

POSITIVE LOGITS

 simplified

0.91

 explaining

0.90

 explain

0.90

 explanations

0.90

 explanation

0.87

 understandable

0.85

explain

0.84

 layman

0.83

simplified

0.81

 Explained

0.81

Activations Density 0.276%

phrases related to health communication and understanding

Simplified explanations

plain language explanations

No Comments

No Known Activations