INDEX

Explanations

references to programming constructs and exceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

tagHelperRunner

-1.06

:✨

-0.91

 EconPapers

-0.83

帖最后由

-0.77

 nakalista

-0.73

 '\\;'

-0.72

ChildIndex

-0.71

ArgsConstructor

-0.70

GEBURTSDATUM

-0.69

NameInMap

-0.68

POSITIVE LOGITS

 brady

0.51

 Pantheon

0.50

''}

0.50

 eingeladen

0.50

 preocupes

0.48

addHandler

0.48

 Pons

0.47

 TextStyle

0.47

babu

0.46

!!}

0.46

Activations Density 0.109%

references to programming constructs and exceptions

No Comments

No Known Activations