INDEX

Explanations

technical terms related to geometry and transformation in objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

 InputDecoration

-0.31

clusal

-0.27

 Hutton

-0.24

niña

-0.24

 Canti

-0.23

flashdata

-0.23

 citas

-0.23

 Functional

-0.23

GA

-0.23

 surging

-0.23

POSITIVE LOGITS

 ninety

0.73

addGap

0.66

 EconPapers

0.65

Personendaten

0.63

الدراسه

0.63

 turnaround

0.62

 semicirc

0.61

IUrlHelper

0.61

 Ninety

0.60

Tikang

0.58

Activations Density 0.308%

technical terms related to geometry and transformation in objects

No Comments

No Known Activations