INDEX

Explanations

mathematical notations and symbols used in formal definitions or expressions

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

Tokens preceding math expressions

np_acts-logits-general · gemini-2.0-flash

$(A^{(i)})_{i\ge 1}$ i.i.d. sequence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

MigrationBuilder

-0.74

AndEndTag

-0.71

 pinulongan

-0.70

الحياه

-0.67

tagHelperRunner

-0.67

EndContext

-0.66

msgTypes

-0.66

Ӕ

-0.66

iſen

-0.65

 محفوظة

-0.65

POSITIVE LOGITS

=('

0.59

}=(

0.59

)=(

0.58

}=(\

0.54

=(

0.54

=("

0.49

((

0.47

=((

0.43

]=(

0.43

=(

0.43

Activations Density 1.078%

mathematical notations and symbols used in formal definitions or expressions

Tokens preceding math expressions

$(A^{(i)})_{i\ge 1}$ i.i.d. sequence

No Comments

No Known Activations