INDEX

Explanations

end-of-comment indicators and potential closing syntax in code

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

Code, identifiers, and programming-related text

np_acts-logits-general · gemini-2.0-flash

district court, possible, vipectus, calculation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵↵

-0.57

-0.56

-0.55

<eos>

-0.54

...

-0.54

 never

-0.53

 attempts

-0.47

ichon

-0.47

 with

-0.47

-0.46

POSITIVE LOGITS

 ExecuteAsync

1.17

]")]

1.08

$")

1.01

rungsseite

1.00

 AssemblyTitle

0.97

__':

0.97

 للاسماء

0.94

 autorytatywna

0.94

tvguidetime

0.92

Datuak

0.91

Activations Density 0.041%

end-of-comment indicators and potential closing syntax in code

Code, identifiers, and programming-related text

district court, possible, vipectus, calculation

No Comments

No Known Activations