INDEX

Explanations

references to items, products, or materials that are being shared or reprinted

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

Reprints, product, share, common

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

 Bracken

-0.46

("/")

-0.45

atha

-0.45

="/">

-0.44

xca

-0.42

Tor

-0.42

 Maurer

-0.42

 McCulloch

-0.41

 Carrillo

-0.41

 Hull

-0.41

POSITIVE LOGITS

品

2.45

品

1.82

品的

1.68

品の

1.45

품

1.42

品です

1.21

 phẩm

1.19

一品

0.88

 product

0.78

Product

0.71

Activations Density 0.001%

references to items, products, or materials that are being shared or reprinted

Reprints, product, share, common

No Comments

No Known Activations