INDEX

Explanations

references to the term "active" in various contexts

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

"active" and its related forms

np_acts-logits-general · gemini-2.0-flash

active followed by noun

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

yntaxException

-0.66

 AspNetCore

-0.65

 betweenstory

-0.65

Personensuche

-0.61

 CreateTagHelper

-0.60

adaptiveStyles

-0.59

torta

-0.58

nought

-0.58

epam

-0.58

odils

-0.58

POSITIVE LOGITS

 ACTIVE

0.91

active

0.83

ACTIVE

0.81

Inactive

0.81

 Active

0.80

 isActive

0.79

Active

0.78

getActive

0.77

actively

0.77

 active

0.76

Activations Density 0.107%

references to the term "active" in various contexts

"active" and its related forms

active followed by noun

No Comments

No Known Activations