INDEX

Explanations

code annotations and attributes used in programming

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

install and delete actions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 betweenstory

-0.63

}}}}

-0.61

ChildScrollView

-0.59

tagHelperRunner

-0.58

</tfoot>

-0.54

parsedMessage

-0.54

rungsseite

-0.54

BagConstraints

-0.52

setVerticalGroup

-0.52

SequentialGroup

-0.50

POSITIVE LOGITS

DllImport

0.69

//

0.45

Digite

0.39

utschen

0.39

 précédente

0.38

 Microsoft

0.37

 tidigare

0.36

Unmanaged

0.36

 ComVisible

0.36

ähig

0.35

Activations Density 0.002%

code annotations and attributes used in programming

install and delete actions

No Comments

No Known Activations