INDEX

Explanations

identifiers or variables related to programming or data structures

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

HTML closing tags and URLs

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

-0.76

 Infórmanos

-0.64

OpenHelper

-0.61

 betweenstory

-0.61

DeleteBehavior

-0.60

enumii

-0.60

➟

-0.60

}{@

-0.60

 kaarangay

-0.59

 snippetHide

-0.59

POSITIVE LOGITS

 răsp

0.34

preventDefault

0.33

 erfahren

0.32

 Karya

0.32

 Verfassung

0.31

qxd

0.31

ylvan

0.31

 Führung

0.30

 UIKit

0.30

 Ávila

0.30

Activations Density 0.012%

identifiers or variables related to programming or data structures

HTML closing tags and URLs

No Comments

No Known Activations