INDEX

Explanations

identifiers and key-value pairs typically found in database queries and relationships

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

code, id, pk, time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

帖最后由

-0.88

AddTagHelper

-0.77

EDEFAULT

-0.72

IsMutable

-0.71

AndEndTag

-0.69

 يتيمه

-0.69

 ModelExpression

-0.68

 дописавши

-0.68

migrationBuilder

-0.67

+#+#

-0.65

POSITIVE LOGITS

 abordagem

0.38

 Vernunft

0.36

 schedule

0.34

 navideños

0.33

 Moscú

0.32

 Gehalt

0.31

 Vielfalt

0.31

 tirantes

0.30

 veřej

0.28

 creemos

0.28

Activations Density 0.019%

identifiers and key-value pairs typically found in database queries and relationships

code, id, pk, time

No Comments

No Known Activations