INDEX

Explanations

elements related to artificial neural networks and their architectures

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

Neural network layers

np_acts-logits-general · gemini-2.0-flash

neural network layers and architecture

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

:✨

-0.74

+#+#

-0.74

MeasureSpec

-0.57



-0.57

CloseOperation

-0.56

 дописавши

-0.52

 Roskov

-0.52

.*")]

-0.51

IntoConstraints

-0.51

LogFactory

-0.51

POSITIVE LOGITS

 network

0.96

 hidden

0.88

 networks

0.86

 neural

0.85

 activation

0.85

 layer

0.84

 Network

0.83

 training

0.82

 Hidden

0.81

network

0.81

Activations Density 0.387%

elements related to artificial neural networks and their architectures

Neural network layers

neural network layers and architecture

No Comments

No Known Activations