INDEX

Explanations

specific terms related to notices and reports, particularly in the context of medical and scientific research

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

Tokens after prepositions "of" or "in"

np_acts-logits-general · gemini-2.0-flash

Kuala Lumpur

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.84

InjectAttribute

-0.68

AccessorTable

-0.68

<unused79>

-0.67

<unused71>

-0.67

<unused16>

-0.67

<unused8>

-0.66

<unused14>

-0.66

<unused1>

-0.66

[@BOS@]

-0.66

POSITIVE LOGITS

Nationalité

0.30

XmlAccessType

0.29

立

0.27

0.26

 Haig

0.26

lé

0.25

0.24

TYPED

0.23

Népesség

0.23

《

0.23

Activations Density 0.114%

specific terms related to notices and reports, particularly in the context of medical and scientific research

Tokens after prepositions "of" or "in"

Kuala Lumpur

No Comments

No Known Activations