INDEX

Explanations

technical terms related to transformers in software or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

nesc

-0.59

AndEndTag

-0.50

englanniksi

-0.50

 Gier

-0.50

ByDefault

-0.49

 المعيارى

-0.48

odio

-0.48

expandindo

-0.47

PerformLayout

-0.46

 Scope

-0.46

POSITIVE LOGITS

fortawesome

0.63

 "));

0.61

SourceChecksum

0.60

AndroidJUnit

0.59

 pinulongan

0.57

Geplaatst

0.57

 Оно

0.57

uxxxx

0.57

webElementGuid

0.56

consulté

0.56

Activations Density 0.172%

technical terms related to transformers in software or programming contexts

No Comments

No Known Activations