INDEX

Explanations

mathematical expressions and notations

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

Mathematical notation

np_acts-logits-general · gemini-2.0-flash

mathematical and structural symbols

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

</b>

-0.59

↵↵

-0.55

waitKey

-0.52

<eos>

-0.48

</strong>

-0.48

omitempty

-0.43

</h2>

-0.42

DockStyle

-0.42

-0.40

hu

-0.40

POSITIVE LOGITS

 itſelf

0.88

رشف

0.80

 nakalista

0.79

dafx

0.78

 Monfieur

0.75

 Avignon

0.74

 purpoſe

0.73

 ་་

0.73

 متعلقه

0.70

 Mexicans

0.70

Activations Density 0.519%

mathematical expressions and notations

Mathematical notation

mathematical and structural symbols

No Comments

No Known Activations