INDEX

Explanations

comparative terms indicating levels or qualities, particularly those related to efficiency and measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

newtheorem

-0.34

 central

-0.31

 يتيمه

-0.29

bl

-0.28

 tightly

-0.28

Flo

-0.28

 fallo

-0.27

BL

-0.27

cob

-0.27

ci

-0.27

POSITIVE LOGITS

TypedDataSet

0.69

xase

0.68

󠁴

0.67

IntoConstraints

0.63

IUrlHelper

0.63

InjectAttribute

0.62

 évêque

0.62

IBOutlet

0.61

 resourceCulture

0.60

 gynhyrchwyd

0.59

Activations Density 1.658%

comparative terms indicating levels or qualities, particularly those related to efficiency and measurement

No Comments

No Known Activations