INDEX

Explanations

mathematical symbols and expressions involving sets or algebraic structures

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

Expressions enclosed in `${}`

np_acts-logits-general · gemini-2.0-flash

toric variety $\PP_{\Sigma}$

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

tez

-0.57

engah

-0.49

arc

-0.49

ára

-0.48

 Pola

-0.48

</strong>

-0.48

Mint

-0.47

 Harrison

-0.47

벌

-0.47

 поле

-0.47

POSITIVE LOGITS

 الحره

0.88

 متعلقه

0.82

AccessorTable

0.78

 numberWith

0.77

__":

0.70

 MainAxisSize

0.70

 beginnetje

0.67

}^{

0.65

 }^{\

0.64

Hochspringen

0.63

Activations Density 0.207%

mathematical symbols and expressions involving sets or algebraic structures

Expressions enclosed in `${}`

toric variety $\PP_{\Sigma}$

No Comments

No Known Activations