INDEX

Explanations

numerical ranges and measures associated with scientific or technical data

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

quantities and ranges

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

ſelf

-0.52

testify

-0.50

yarnpkg

-0.48

ſelves

-0.47

 surla

-0.45

 IBOutlet

-0.42



-0.42

جستارهای

-0.41

saraba

-0.40

CDCl

-0.39

POSITIVE LOGITS

 ffilmiau

0.44

iking

0.42

bereiche

0.41

 okolo

0.41

Diweddarwch

0.41

usive

0.40

 Measurements

0.40

AddTagHelper

0.40

 kolem

0.40

exer

0.40

Activations Density 0.062%

numerical ranges and measures associated with scientific or technical data

quantities and ranges

No Comments

No Known Activations