INDEX

Explanations

opening and closing parentheses in code

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

protoimpl

-0.63

tagHelperRunner

-0.53

ronpa

-0.50

mister

-0.49

 noiembrie

-0.49

endcsname

-0.48

Cristo

-0.46

γμα

-0.46

íně

-0.45

<em>

-0.45

POSITIVE LOGITS

AutoScale

1.05

UnusedPrivate

0.99

Архівовано

0.93

AutoSize

0.91

 defaultstate

0.88

RunAsync

0.87

 فريبيس

0.85

 cellpadding

0.85

 viewDidLoad

0.84

MemoryWarning

0.83

Activations Density 0.033%

opening and closing parentheses in code

No Comments

No Known Activations