INDEX

Explanations

mathematical notations and symbols in textual content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 كومونز

-0.82

ftagPool

-0.77

AndEndTag

-0.77

ьаж

-0.72

 Akismet

-0.69

 surla

-0.69

 المعيارى

-0.67

tonsoft

-0.66

httphttps

-0.66

 Exactos

-0.65

POSITIVE LOGITS

0.40

Following

0.32

bag

0.31

0.30

0.28

book

0.27

 Following

0.27

Later

0.27

Activations Density 1.571%

mathematical notations and symbols in textual content

No Comments

No Known Activations