INDEX

Explanations

words or symbols of significance in technical writing and research papers, especially citations and references

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AddTagHelper

-0.87

ThroughAttribute

-0.80

Personensuche

-0.76

IVEREF

-0.68

StoryboardSegue

-0.66

 kasarigan

-0.66

Geplaatst

-0.65

 saites

-0.65

ReusableCell

-0.64

webElementXpaths

-0.63

POSITIVE LOGITS

 AssemblyTitle

0.58

]--;

0.51

 Estadual

0.49

 vecchia

0.48

 paloma

0.47

<>

0.45

 STAMP

0.44

didSet

0.44

 deliberately

0.43

 roost

0.42

Activations Density 34.437%

words or symbols of significance in technical writing and research papers, especially citations and references

No Comments

No Known Activations