INDEX

Explanations

terms related to anti-microbial and anti-inflammatory properties

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

"Anti" prefix followed by medical/scientific terms

np_acts-logits-general · gemini-2.0-flash

"anti" prefix indicating counteraction

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

expandindo

-0.77

 AssemblyCompany

-0.59

uggets

-0.59

 calendriers

-0.58

URLException

-0.57

 NgModule

-0.56

 jScrollPane

-0.53

 NSCoder

-0.51

⇑

-0.50

BeginContext

-0.48

POSITIVE LOGITS

 Anti

1.16

Anti

1.14

 anti

1.06

 antig

1.03

 ANTI

0.99

anti

0.96

ANT

0.95

 Анти

0.95

 antis

0.91

Анти

0.91

Activations Density 0.140%

terms related to anti-microbial and anti-inflammatory properties

"Anti" prefix followed by medical/scientific terms

"anti" prefix indicating counteraction

No Comments

No Known Activations