INDEX

Explanations

technical terms and phrases related to neural network training and model saving in TensorFlow

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 immédi

-0.46

Auf

-0.44

 culturel

-0.43

 culturelle

-0.43

 verità

-0.43

anta

-0.41

 diritti

-0.41

<?

-0.41

 personnelle

-0.40

 pattes

-0.40

POSITIVE LOGITS

ніципалі

0.98

 jsPsych

0.98

 /\.(

0.96

发表于

0.91

WithIOException

0.91

parsedMessage

0.90

RegressionTest

0.88

 kasarigan

0.88

Xna

0.84

twimg

0.84

Activations Density 0.089%

technical terms and phrases related to neural network training and model saving in TensorFlow

No Comments

No Known Activations