INDEX

Explanations

annotations related to entities and their properties

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

Annotation SerializedName

np_acts-logits-general · gemini-2.0-flash

java annotations and keywords

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

\'

-0.54

 dual

-0.54

-0.53

кисло

-0.53

-0.51

lit

-0.51

о

-0.51

mer

-0.49

ob

-0.49

POSITIVE LOGITS

IsMutable

0.89

NUMX

0.72

 propOrder

0.70

WebVitals

0.70

//*/

0.69

BagConstraints

0.68

middels

0.67

}</

0.66

Repost

0.66

javax

0.66

Activations Density 0.016%

annotations related to entities and their properties

Annotation SerializedName

java annotations and keywords

No Comments

No Known Activations