INDEX

Explanations

references to medical information and conditions

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

Text after numbers or symbols

np_acts-logits-general · gemini-2.0-flash

return filings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Geplaatst

-0.67

AxisAlignment

-0.59

 apellido

-0.58

 justement

-0.57

 isKindOfClass

-0.55

 atributo

-0.52

 consultato

-0.52

Datuak

-0.52

esseur

-0.51

 cref

-0.51

POSITIVE LOGITS

<eos>

1.15

etc

0.98

↵↵

0.96

などなど

0.94

})();

0.93

↵↵↵

0.93

""".

0.88

↵↵↵↵

0.87

etc

0.86

))))))))

0.86

Activations Density 0.808%

references to medical information and conditions

Text after numbers or symbols

return filings

No Comments

No Known Activations