INDEX

Explanations

terms associated with the concept of orientation or alignment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

RectangleBorder

-0.83

 AssemblyVersion

-0.81

 disambiguazione

-0.79

+#+#

-0.77

verwijspagina

-0.77

دانشنامهٔ

-0.68

AndEndTag

-0.66

afficheront

-0.65

featureID

-0.64

StructEnd

-0.63

POSITIVE LOGITS

 orientation

0.77

Session

0.70

Orientation

0.70

 Orientation

0.68

orientation

0.68

 Session

0.60

 session

0.59

 orient

0.59

Ep

0.56

orient

0.56

Activations Density 0.598%

terms associated with the concept of orientation or alignment

No Comments

No Known Activations