INDEX

Explanations

features related to software updates and functionalities

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

Adding functionality/features

np_acts-logits-general · gemini-2.0-flash

adds new features and capabilities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PerformLayout

-0.94

sizeCache

-0.81

RegressionTest

-0.79

IVEREF

-0.78

tagHelperRunner

-0.73

WebVitals

-0.72

AndEndTag

-0.72

ChildScrollView

-0.69

 becauſe

-0.68

AsUp

-0.68

POSITIVE LOGITS

 auto

1.14

 ability

1.13

 automatic

1.09

 Auto

0.97

automatic

0.94

Automatic

0.85

 Automatic

0.85

 optional

0.82

 возможность

0.82

 capability

0.80

Activations Density 0.631%

features related to software updates and functionalities

Adding functionality/features

adds new features and capabilities

No Comments

No Known Activations