INDEX

Explanations

words and phrases indicating conditions or specifications around configurations and settings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 queſta

-0.65

enderror

-0.63

 Приступљено

-0.62

rawDesc

-0.60

PerformLayout

-0.60

 Roskov

-0.59

**/

-0.58

TypedDataSet

-0.58

$_"

-0.57

RuleContext

-0.57

POSITIVE LOGITS

the

0.67

 consultato

0.43

the

0.37

DockStyle

0.34

 את

0.33

专属

0.32

en

0.32

revet

0.30

 아니

0.30

 CanadaChoose

0.29

Activations Density 0.733%

words and phrases indicating conditions or specifications around configurations and settings

No Comments

No Known Activations