INDEX

Explanations

terms related to diffusion processes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 estimés

-0.88

 propOrder

-0.88

 Barlow

-0.86

contentLoaded

-0.85

 ExecuteAsync

-0.85

ValueStyle

-0.84

odeon

-0.83

]))

-0.82

SequentialGroup

-0.82

 RestTemplate

-0.81

POSITIVE LOGITS

ized

0.71

 Keats

0.67

Hô

0.66

 setOpen

0.66

 Bosco

0.64

––––

0.64

 Holz

0.62

Keb

0.61

irling

0.60

opha

0.59

Activations Density 1.037%

terms related to diffusion processes in various contexts

No Comments

No Known Activations