INDEX

Explanations

various symbols, particularly underscores and slashes, indicating formatting or structure in textual data

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

process performance cluster stress

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

 hendes

-0.27

 nemlig

-0.26

 TAMBÉM

-0.26

 derfor

-0.25

WebElementEntity

-0.24

 rowspan

-0.24

 därför

-0.24

 Libertadores

-0.24

krát

-0.23

 Italijani

-0.23

POSITIVE LOGITS

 autorytatywna

0.79

MigrationBuilder

0.74



0.72

 AssemblyTitle

0.71

 للمعارف

0.70

 EconPapers

0.68

 ✭✭

0.67

ніципалі

0.66

 protoimpl

0.65

<unused28>

0.65

Activations Density 0.007%

various symbols, particularly underscores and slashes, indicating formatting or structure in textual data

process performance cluster stress

No Comments

No Known Activations