INDEX

Explanations

programming-related terms, especially those pertaining to functions and parameters

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

Code-related tokens followed by specific punctuation or symbols

np_acts-logits-general · gemini-2.0-flash

programming variables

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

delli

-0.55

-0.49

]=="

-0.47

</h2>

-0.45

Gre

-0.45

bio

-0.44

<eos>

-0.44

-0.43

ixon

-0.41

bus

-0.41

POSITIVE LOGITS

Personensuche

0.93

ⓧ

0.89

 InputDecoration

0.86

AddHtmlAttribute

0.85

يكب

0.82

évaluateur

0.82

MemoryWarning

0.81

 transfieras

0.80

 utafitiHapana

0.80

]")]

0.80

Activations Density 0.114%

programming-related terms, especially those pertaining to functions and parameters

Code-related tokens followed by specific punctuation or symbols

programming variables

No Comments

No Known Activations