INDEX

Explanations

terms related to weight and heaviness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 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

Cyfeiriadau

-0.58

tagHelperRunner

-0.53

 Paglinawan

-0.53

存于互联网档案馆

-0.53

vinfos

-0.52

httphttps

-0.52

parsedMessage

-0.49

yntaxException

-0.49

 schloss

-0.47

prepareStatement

-0.46

POSITIVE LOGITS

 weight

1.09

 Weight

0.94

Weight

0.91

 heavier

0.89

 weighing

0.89

weight

0.89

 weights

0.88

 WEIGHT

0.84

 weigh

0.82

 weighs

0.82

Activations Density 0.353%

terms related to weight and heaviness

No Comments

No Known Activations