INDEX

Explanations

terms related to health and medical conditions involving specific diseases and their implications

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

Tokens before adverbs/descriptors of scientific studies

np_acts-logits-general · gemini-2.0-flash

new research findings

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

^(@)

-0.71

CppMethod

-0.69

Eksterne

-0.69

MLLoader

-0.65

Conseils

-0.64

 चीज़ों

-0.64

 ProductService

-0.63

 CreateTagHelper

-0.63

principalColumn

-0.62

amię

-0.62

POSITIVE LOGITS

 recently

0.55

 wondering

0.54

Recently

0.53

 Recently

0.52

recently

0.50

 investigate

0.48

 недавно

0.48

 Little

0.47

 investigated

0.47

 unexplored

0.46

Activations Density 1.149%

terms related to health and medical conditions involving specific diseases and their implications

Tokens before adverbs/descriptors of scientific studies

new research findings

No Comments

No Known Activations